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

    Neuronpedia

    INDEX
    Explanations

    Online discussions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     outgoing
    -0.07
     bp
    -0.07
    Ng
    -0.06
    ोफ
    -0.06
    #index
    -0.06
    Sit
    -0.06
    lecture
    -0.06
     Monetary
    -0.06
    .setText
    -0.06
    _yield
    -0.06
    POSITIVE LOGITS
    admins
    0.07
     chắc
    0.07
     "|"
    0.06
     玩家
    0.06
    111
    0.06
     п
    0.06
    frac
    0.06
     butcher
    0.06
    sects
    0.06
     incompatible
    0.06
    Act Density 0.006%

    No Known Activations