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

    Neuronpedia

    INDEX
    Explanations

    c

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -utils
    -0.07
    ーチ
    -0.07
    ayment
    -0.06
    ίζ
    -0.06
    odyn
    -0.06
     tụ
    -0.06
     hver
    -0.06
    uebas
    -0.06
    ैं,
    -0.06
    awa
    -0.06
    POSITIVE LOGITS
     craftsm
    0.08
    屏
    0.07
    494
    0.07
    _Obj
    0.07
     tropical
    0.06
     enlisted
    0.06
    .sample
    0.06
     Behaviour
    0.06
    .Emit
    0.06
     exotic
    0.06
    Act Density 0.000%

    No Known Activations