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

    Neuronpedia

    INDEX
    Explanations

    zA-Z0-9 -

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    の概要
    -0.99
     even
    -0.93
     Speisen
    -0.91
     errors
    -0.88
     others
    -0.88
     Erzb
    -0.87
     проекты
    -0.85
    mıştır
    -0.84
     versus
    -0.84
     its
    -0.83
    POSITIVE LOGITS
    z
    1.05
    Джерела
    0.90
    az
    0.89
    很好的
    0.88
     fonde
    0.87
     Confused
    0.87
     stockfoto
    0.86
    ⋁
    0.86
     fraî
    0.85
     Leth
    0.84
    Act Density 0.003%

    No Known Activations