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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _PH
    -0.07
     inhibitors
    -0.07
    velocity
    -0.07
    _eof
    -0.07
     cakes
    -0.06
    跑
    -0.06
     Liebe
    -0.06
    ensation
    -0.06
     FORM
    -0.06
    packet
    -0.06
    POSITIVE LOGITS
     lokale
    0.07
     industries
    0.06
    _production
    0.06
     Canc
    0.06
    048
    0.06
    ガ
    0.06
     صور
    0.06
     redirection
    0.06
     чем
    0.06
     vista
    0.06
    Act Density 0.009%

    No Known Activations