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

    Neuronpedia

    INDEX
    Explanations

    camera lens

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bắc
    -0.07
    -redux
    -0.06
     pest
    -0.06
     tokenize
    -0.06
    เ�
    -0.06
     explode
    -0.06
     منت
    -0.06
     الذه
    -0.06
     pointless
    -0.06
    lacak
    -0.06
    POSITIVE LOGITS
     overseas
    0.06
    ［
    0.06
    .additional
    0.06
     monthly
    0.06
     studios
    0.06
     minimum
    0.06
    誰
    0.06
     factories
    0.06
     increase
    0.06
    κτη
    0.06
    Act Density 0.002%

    No Known Activations