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

    Neuronpedia

    INDEX
    Explanations

    discussion/conversation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    vf
    -0.06
     Haram
    -0.06
     coef
    -0.06
    �
    -0.06
    Feel
    -0.06
    coil
    -0.06
     безопасности
    -0.06
    pg
    -0.06
     spoil
    -0.06
    gas
    -0.06
    POSITIVE LOGITS
     gön
    0.07
    (opt
    0.07
     require
    0.07
    ToObject
    0.06
    _native
    0.06
    (_:
    0.06
    emplate
    0.06
     NT
    0.06
    (',
    0.06
    (ti
    0.06
    Act Density 0.000%

    No Known Activations