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

    Neuronpedia

    INDEX
    Explanations

    progress

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Wald
    -0.08
    лага
    -0.08
     огромное
    -0.07
     nouveau
    -0.07
     nochmal
    -0.07
    perimental
    -0.07
     consequential
    -0.07
    ذا
    -0.07
     puissant
    -0.07
     Once
    -0.07
    POSITIVE LOGITS
     진행
    0.11
    tow
    0.10
     andamento
    0.10
    _PROGRESS
    0.10
    	progress
    0.10
     progresso
    0.09
    .progress
    0.09
     iler
    0.09
     progressing
    0.09
    (progress
    0.09
    Act Density 0.019%

    No Known Activations