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

    Neuronpedia

    INDEX
    Explanations

    questions or phrases that begin with "how."

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

    expressions of doubt or observation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Portale
    -0.47
    sizeCache
    -0.44
    PMailer
    -0.42
    ⓧ
    -0.42
    WriteAttribute
    -0.41
    AndEndTag
    -0.40
    reportWebVitals
    -0.40
     Monteiro
    -0.39
    FieldNumber
    -0.38
    ExecuteReader
    -0.38
    POSITIVE LOGITS
    rungsseite
    0.47
    providedIn
    0.47
    󠁣
    0.43
    Vidite
    0.43
    Personendaten
    0.42
     voeten
    0.41
     Италијани
    0.40
     müm
    0.40
     zosta
    0.39
    easily
    0.37
    Act Density 0.016%

    No Known Activations