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

    Neuronpedia

    INDEX
    Explanations

    references to notable achievements and recognition

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

    established as

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     put
    -0.36
     essay
    -0.35
     shoe
    -0.35
    halten
    -0.34
    ,
    -0.33
    ientôt
    -0.32
     Krueger
    -0.32
    Shoe
    -0.32
    Dif
    -0.32
    fieldset
    -0.32
    POSITIVE LOGITS
     dominance
    0.60
    ⟬
    0.58
     prominence
    0.56
    GEBURTSDATUM
    0.56
    remacy
    0.56
    rungsseite
    0.56
     transfieras
    0.55
    importanza
    0.54
     zoude
    0.54
    levance
    0.54
    Act Density 0.059%

    No Known Activations