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

    Neuronpedia

    INDEX
    Explanations

    terms related to potential outcomes and conditions

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

    past or potential states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nahilalakip
    -0.77
     myſelf
    -0.71
     themſelves
    -0.63
    BufferException
    -0.59
     Houſe
    -0.59
     Anſ
    -0.59
     poffible
    -0.59
     conmigo
    -0.58
     चीज़ों
    -0.57
    GEBURTSDATUM
    -0.57
    POSITIVE LOGITS
     su
    0.44
    pool
    0.42
    table
    0.39
     ut
    0.38
    in
    0.38
    insee
    0.38
    site
    0.37
     grat
    0.37
    su
    0.36
    to
    0.36
    Act Density 0.141%

    No Known Activations