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

    Neuronpedia

    INDEX
    Explanations

    study

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    mesine
    -0.07
    -mask
    -0.06
     faux
    -0.06
    icits
    -0.06
     Isabel
    -0.06
     zum
    -0.06
    .Absolute
    -0.06
    _upload
    -0.06
    polator
    -0.06
    menin
    -0.06
    POSITIVE LOGITS
    aren
    0.07
     sis
    0.06
    لیل
    0.06
     Flyers
    0.06
     Dread
    0.06
    ---@
    0.06
     adventurous
    0.06
    (ERR
    0.06
    uckle
    0.06
    LEGRO
    0.06
    Act Density 0.168%

    No Known Activations