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

    Neuronpedia

    INDEX
    Explanations

    code/technical changes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    '),↵
    -0.07
     sphere
    -0.07
     NSError
    -0.07
    ozem
    -0.07
    -valu
    -0.07
    事件
    -0.07
    -cn
    -0.06
     ud
    -0.06
     Temper
    -0.06
    üç
    -0.06
    POSITIVE LOGITS
    ycastle
    0.07
    amina
    0.06
     هفته
    0.06
     fearless
    0.06
     chassis
    0.06
     investigative
    0.06
    Votre
    0.06
    -*-
    0.06
    黑
    0.06
    Signals
    0.06
    Act Density 0.000%

    No Known Activations