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

    Neuronpedia

    INDEX
    Explanations

    crossing the line

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Disk
    -0.07
    Sky
    -0.07
    yl
    -0.07
     recognizes
    -0.07
     stones
    -0.06
    _append
    -0.06
     груз
    -0.06
     HAR
    -0.06
    lemetry
    -0.06
     Published
    -0.06
    POSITIVE LOGITS
    ाध
    0.07
     mf
    0.06
    .Our
    0.06
     kitten
    0.06
    onaut
    0.06
    ést
    0.06
    ськ
    0.06
     краї
    0.06
    DidAppear
    0.06
    _me
    0.06
    Act Density 0.008%

    No Known Activations