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

    Neuronpedia

    INDEX
    Explanations

    quantity and descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     に
    0.69
    丿
    0.62
    .");
    0.62
     zur
    0.59
     in
    0.58
    .)
    0.58
     upon
    0.58
    ماً
    0.57
     および
    0.56
     dessen
    0.55
    POSITIVE LOGITS
    Some
    0.69
    Few
    0.68
    Many
    0.65
     labai
    0.65
    Credit
    0.64
    Any
    0.64
    não
    0.64
    Often
    0.63
    Stress
    0.63
    Pricing
    0.63
    Act Density 0.031%

    No Known Activations