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

    Neuronpedia

    INDEX
    Explanations

    structured data keys

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     मानबी
    1.44
    Benzoimidazol
    1.42
    HTree
    1.41
     হোমিও
    1.39
     চেতন
    1.38
    ቭ
    1.37
    <unused1604>
    1.36
     переменную
    1.35
     ক্লাশ
    1.35
     ആൻ
    1.35
    POSITIVE LOGITS
    ——
    0.99
    —
    0.89
     —
    0.87
    ;
    0.84
    ,
    0.83
    ~
    0.81
     etc
    0.80
    .
    0.80
    гази
    0.79
     so
    0.77
    Act Density 0.092%

    No Known Activations