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

    Neuronpedia

    INDEX
    Explanations

    $

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ในป
    -0.07
    лением
    -0.07
     btc
    -0.07
    ight
    -0.06
     frequently
    -0.06
    .voice
    -0.06
    .ctrl
    -0.06
    .git
    -0.06
    級
    -0.06
    _OFFSET
    -0.06
    POSITIVE LOGITS
     relevance
    0.06
     enthusi
    0.06
    LEncoder
    0.06
    '],['
    0.06
     liken
    0.06
     judges
    0.06
     fibr
    0.06
     anthology
    0.06
    _good
    0.06
     &#
    0.06
    Act Density 0.006%

    No Known Activations