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

    Neuronpedia

    INDEX
    Explanations

    species

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     conting
    -0.08
     emergencies
    -0.06
     Ariel
    -0.06
    _author
    -0.06
    /details
    -0.06
     вывод
    -0.06
    tz
    -0.06
     lottery
    -0.06
    .motion
    -0.06
    _POINT
    -0.06
    POSITIVE LOGITS
    rhs
    0.07
    orman
    0.07
    .CheckBox
    0.06
    壓
    0.06
     �
    0.06
    폭
    0.06
    _MODEL
    0.06
     şans
    0.06
    -clean
    0.06
    ,'"
    0.06
    Act Density 0.001%

    No Known Activations