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

    Neuronpedia

    INDEX
    Explanations

    direct address

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     domination
    -0.06
     fold
    -0.06
     Submission
    -0.06
     tb
    -0.06
     documentaries
    -0.06
     Kids
    -0.06
    처럼
    -0.06
    طلب
    -0.06
    -tooltip
    -0.06
    пр
    -0.06
    POSITIVE LOGITS
    そんな
    0.07
    ΙΔ
    0.07
    -remove
    0.07
    mapped
    0.06
    _LABEL
    0.06
    يلي
    0.06
    WithName
    0.06
    �
    0.06
    _ident
    0.06
    _GAIN
    0.06
    Act Density 0.086%

    No Known Activations