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

    Neuronpedia

    INDEX
    Explanations

    food preparation steps

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     peroxide
    0.43
    Cars
    0.42
     Per
    0.41
    нову
    0.41
     car
    0.41
     Hispan
    0.40
     glimpses
    0.39
     off
    0.38
    scripts
    0.38
     cast
    0.38
    POSITIVE LOGITS
     Komitet
    0.44
    青少年
    0.38
    herr
    0.38
    ଷ
    0.37
    黍
    0.37
     fabricating
    0.36
    ጀ
    0.36
    oscow
    0.36
     člán
    0.36
    يم
    0.35
    Act Density 0.000%

    No Known Activations