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

    Neuronpedia

    INDEX
    Explanations

    words that express certainty or uncertainty

    oai_token-act-pair · gemini-2.0-flash

    certainly/definitely

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    InvalidProtocol
    -0.77
    SPJ
    -0.75
     getItemCount
    -0.74
    IVEREF
    -0.73
     विश्वसनीयता
    -0.73
    MemoryWarning
    -0.72
    Einfach
    -0.71
    eraard
    -0.71
    اریخ
    -0.71
    FunctionFlags
    -0.70
    POSITIVE LOGITS
     côtés
    0.47
    guém
    0.42
    atius
    0.42
     see
    0.41
     rangs
    0.41
     vatt
    0.40
     intérêt
    0.38
     rätt
    0.37
    חת
    0.37
    動
    0.36
    Act Density 2.229%

    No Known Activations