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

    Neuronpedia

    INDEX
    Explanations

    People, possibly women

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _receiver
    -0.07
    Є
    -0.06
    									↵
    -0.06
    '))->
    -0.06
    ве
    -0.06
     Mev
    -0.06
    傷
    -0.06
    An
    -0.06
     melting
    -0.06
    _require
    -0.06
    POSITIVE LOGITS
     SI
    0.08
    asal
    0.07
     ultra
    0.07
     ffi
    0.06
    ها
    0.06
     rigorous
    0.06
    ��드
    0.06
     appreciate
    0.06
    _API
    0.06
    (LOG
    0.06
    Act Density 0.006%

    No Known Activations