Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    emotional expressions and sentiments related to connection and personal experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Intensifiers such as "so", "too", "quite", "more"

    np_acts-logits-general · gemini-2.0-flash

    so much, so far, so well

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nahilalakip
    -0.84
    ///</
    -0.66
    الإنجليزية
    -0.62
    Portail
    -0.59
     emel
    -0.55
    gania
    -0.50
    Palmar
    -0.50
     medel
    -0.50
    bory
    -0.50
     препратки
    -0.49
    POSITIVE LOGITS
     typelib
    0.60
     very
    0.56
    auteuil
    0.53
    ároz
    0.53
     greatly
    0.52
     absolutely
    0.52
     useStyles
    0.52
     dearly
    0.51
    dfunding
    0.51
    DoubleQuotes
    0.50
    Act Density 0.326%

    No Known Activations