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

    Neuronpedia

    INDEX
    Explanations

    markup language keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    on
    0.47
    o
    0.45
    remove
    0.43
     Page
    0.43
    expired
    0.42
    0.42
    header
    0.41
     Le
    0.40
    hen
    0.40
    oo
    0.40
    POSITIVE LOGITS
    ับสนุน
    0.45
     таксама
    0.43
     compan
    0.43
     comulti
    0.43
    ㄗ
    0.43
     insures
    0.42
    зидента
    0.42
     murderous
    0.41
    ㄏ
    0.41
     zmdi
    0.41
    Act Density 0.001%

    No Known Activations