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

    Neuronpedia

    INDEX
    Explanations

    regulations Immunity source

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     متنوع
    1.14
     receptionist
    1.07
     satisfying
    1.00
     thriller
    1.00
     verschiedenen
    1.00
     yearbook
    1.00
     consectetur
    0.98
     technik
    0.98
     realizacji
    0.98
     evocative
    0.98
    POSITIVE LOGITS
    약을
    0.88
    স্তা
    0.81
     insult
    0.80
    直線
    0.78
    苟
    0.75
    Failed
    0.75
    不能
    0.74
    மய
    0.73
    되지
    0.72
     Failed
    0.72
    Act Density 0.000%

    No Known Activations