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

    Neuronpedia

    INDEX
    Explanations

    questions and speculations about unknowns or uncertainties

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

    unknown possibilities and questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ConstraintMaker
    -0.71
     متعلقه
    -0.60
    NonUser
    -0.58
    ôtel
    -0.58
    𓃵
    -0.54
    AISSEE
    -0.53
    tså
    -0.52
    enservice
    -0.52
    ronpa
    -0.52
     HasFactory
    -0.50
    POSITIVE LOGITS
    ResumeLayout
    0.43
     potential
    0.42
     unknown
    0.40
     unpredictable
    0.39
    说不定
    0.37
    randomUUID
    0.37
    readObject
    0.36
    unknown
    0.36
     interesting
    0.36
    SerializedName
    0.36
    Act Density 0.024%

    No Known Activations