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

    Neuronpedia

    INDEX
    Explanations

    Text snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    745
    -0.07
     responsibility
    -0.06
     bourbon
    -0.06
    Province
    -0.06
     Anderson
    -0.06
     useless
    -0.06
    hurst
    -0.06
    ，小
    -0.06
     新
    -0.06
     صالح
    -0.06
    POSITIVE LOGITS
     Aç
    0.07
    //---------------------------------------------------------------------------↵↵
    0.07
    atican
    0.06
     unab
    0.06
    (sz
    0.06
     *)((
    0.06
    ]))↵↵
    0.06
     onChanged
    0.06
    Respond
    0.06
    >()->
    0.06
    Act Density 0.117%

    No Known Activations