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

    Neuronpedia

    INDEX
    Explanations

    html and code tags

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    thren
    -0.84
     }:
    -0.78
    tabol
    -0.77
     vaan
    -0.77
    sys
    -0.76
    free
    -0.75
     свобод
    -0.75
     Ee
    -0.75
     hounds
    -0.75
    (_,
    -0.74
    POSITIVE LOGITS
     çekilen
    0.86
    Ainsi
    0.81
     nenhuma
    0.77
     will
    0.77
    cticide
    0.76
     Hemos
    0.75
     отсут
    0.75
    دين
    0.74
    Donde
    0.74
     häufigsten
    0.74
    Act Density 0.029%

    No Known Activations