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

    Neuronpedia

    INDEX
    Explanations

    code/stubs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     weighing
    -0.08
     venues
    -0.07
    Depart
    -0.07
     sto
    -0.06
    REDIS
    -0.06
    óng
    -0.06
    stants
    -0.06
    _week
    -0.06
    ecessarily
    -0.06
    ΟΓ
    -0.06
    POSITIVE LOGITS
    /B
    0.06
    /M
    0.06
    BD
    0.06
     Dram
    0.06
    /apple
    0.06
    -б
    0.06
    iphers
    0.06
    unnable
    0.06
     autistic
    0.06
     코로나
    0.06
    Act Density 0.000%

    No Known Activations