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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    õ
    -0.07
    .Content
    -0.07
     traged
    -0.07
     publicKey
    -0.07
    .Win
    -0.06
    .CONTENT
    -0.06
     Picker
    -0.06
    âce
    -0.06
    민
    -0.06
    атів
    -0.06
    POSITIVE LOGITS
    (ed
    0.06
     skim
    0.06
     Flight
    0.06
    电子
    0.06
     "./
    0.06
     абсолютно
    0.06
     engage
    0.06
     ras
    0.06
    )((((
    0.06
     retali
    0.06
    Act Density 0.004%

    No Known Activations