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

    Neuronpedia

    INDEX
    Explanations

    consider

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    GPC
    -0.08
    :NO
    -0.08
    情侣
    -0.07
     grey
    -0.07
    倦
    -0.07
    خدم
    -0.07
    變得
    -0.07
     ease
    -0.07
    Codec
    -0.07
     Offers
    -0.07
    POSITIVE LOGITS
    .cs
    0.07
    .prot
    0.07
    '^$',
    0.07
     bụ
    0.07
    濋
    0.07
    .iteritems
    0.06
    ᨲ
    0.06
     hockey
    0.06
     compute
    0.06
    揪
    0.06
    Act Density 0.006%

    No Known Activations