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

    Neuronpedia

    INDEX
    Explanations

    Disclaimers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     travel
    -0.07
     oc
    -0.07
    odge
    -0.07
     Assistance
    -0.07
    /bootstrap
    -0.07
    开具
    -0.06
     תו
    -0.06
    .cm
    -0.06
     Scott
    -0.06
     farewell
    -0.06
    POSITIVE LOGITS
    埝
    0.07
    ゃ
    0.07
    UPDATED
    0.07
    YNAMIC
    0.07
    EXAMPLE
    0.07
     FileName
    0.07
     fences
    0.06
     ‎
    0.06
     peso
    0.06
    licos
    0.06
    Act Density 0.210%

    No Known Activations