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

    Neuronpedia

    INDEX
    Explanations

    HTML head tag

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     heartwarming
    0.85
     CHF
    0.83
     MGM
    0.81
     ensimmä
    0.81
     eten
    0.80
     amazingly
    0.80
     całej
    0.79
     Insgesamt
    0.79
     SDGs
    0.79
     Mô
    0.78
    POSITIVE LOGITS
    ᑉ
    0.85
    economia
    0.76
    entend
    0.74
    ;"
    0.73
    んだ
    0.73
    ностях
    0.73
    EPEND
    0.72
    ;")
    0.71
    onSubmit
    0.71
    setFixedHeight
    0.71
    Act Density 0.001%

    No Known Activations