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

    Neuronpedia

    INDEX
    Explanations

    frame

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    เคล
    -0.07
    �
    -0.06
     rob
    -0.06
     util
    -0.06
     Bolt
    -0.06
    /os
    -0.06
    Dig
    -0.06
    Ol
    -0.06
     piping
    -0.06
     jelly
    -0.06
    POSITIVE LOGITS
     camel
    0.07
    committee
    0.07
     overturned
    0.07
     suspected
    0.06
     predicts
    0.06
    ẩu
    0.06
     experienced
    0.06
    memiş
    0.06
    Instructions
    0.06
     violently
    0.06
    Act Density 0.001%

    No Known Activations