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

    Neuronpedia

    INDEX
    Explanations

    increased

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    没办法
    -0.08
    nown
    -0.07
    ++.
    -0.07
    好的
    -0.07
     kidney
    -0.07
    Grace
    -0.07
    revision
    -0.07
     DSL
    -0.07
    July
    -0.07
     um
    -0.07
    POSITIVE LOGITS
    פעיל
    0.07
    _PRESENT
    0.07
    _%
    0.06
    HashCode
    0.06
    ⎾
    0.06
     hükü
    0.06
    精神文明
    0.06
    _Min
    0.06
    (headers
    0.06
    心目
    0.06
    Act Density 0.016%

    No Known Activations