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

    Neuronpedia

    INDEX
    Explanations

    donations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Space
    -0.07
    rypt
    -0.07
     progressing
    -0.07
    ations
    -0.07
    ёт
    -0.06
    AGMENT
    -0.06
    etus
    -0.06
     bandwidth
    -0.06
    анием
    -0.06
     strain
    -0.06
    POSITIVE LOGITS
    [code
    0.07
    だった
    0.07
     بإ
    0.06
    ではない
    0.06
    .filtered
    0.06
    민주
    0.06
    ptest
    0.06
     ".$
    0.06
    .secret
    0.06
     Đặc
    0.06
    Act Density 0.101%

    No Known Activations