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

    Neuronpedia

    INDEX
    Explanations

    recognized

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    غيل
    -0.06
    relation
    -0.06
    _THREAD
    -0.06
     vocals
    -0.06
    aln
    -0.06
    521
    -0.06
    782
    -0.06
    나
    -0.06
    elve
    -0.06
    615
    -0.06
    POSITIVE LOGITS
    _again
    0.08
     výraz
    0.07
     confirmation
    0.06
     čtvrt
    0.06
    …"
    0.06
    Під
    0.06
    IRONMENT
    0.06
    //
↵
↵
    0.06
        ↵↵
    0.06
    """
↵
    0.06
    Act Density 0.013%

    No Known Activations