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

    Neuronpedia

    INDEX
    Explanations

    saying goodbye or endings

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (frames
    -0.07
    718
    -0.06
    ifference
    -0.06
    这
    -0.06
     Sinn
    -0.06
     coaches
    -0.06
     뜻
    -0.06
     faculty
    -0.06
    .ToArray
    -0.06
    Mult
    -0.06
    POSITIVE LOGITS
     Need
    0.06
     hlavní
    0.06
     �
    0.06
     Indust
    0.06
    .timeScale
    0.06
    ného
    0.06
     [].
    0.06
     Inc
    0.06
     Stainless
    0.06
     realloc
    0.06
    Act Density 0.097%

    No Known Activations