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

    Neuronpedia

    INDEX
    Explanations

    pm

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     transformer
    -0.07
    -success
    -0.07
     List
    -0.06
     ند
    -0.06
    _info
    -0.06
     books
    -0.06
    300
    -0.06
    าส
    -0.06
    .books
    -0.06
    Canvas
    -0.06
    POSITIVE LOGITS
     interpolate
    0.07
    /><
    0.07
    eresa
    0.07
    (IR
    0.07
    IBUTE
    0.07
     Shame
    0.07
     ±
    0.07
     mí
    0.06
     tir
    0.06
    마
    0.06
    Act Density 0.005%

    No Known Activations