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

    Neuronpedia

    INDEX
    Explanations

    size

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Fashion
    -0.06
    lrt
    -0.06
     glued
    -0.06
    QRS
    -0.06
    oba
    -0.06
    ख
    -0.06
     Flor
    -0.06
     directors
    -0.06
     --------------------
    -0.06
    .Av
    -0.06
    POSITIVE LOGITS
    identally
    0.06
    fty
    0.06
     अगर
    0.06
    }\.[
    0.06
    FORM
    0.06
    ่น
    0.06
     Ember
    0.06
    ually
    0.06
     hypers
    0.06
     สถาน
    0.06
    Act Density 0.047%

    No Known Activations