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

    Neuronpedia

    INDEX
    Explanations

    enum values and definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ان
    1.50
    Methoxy
    1.38
    REIB
    1.34
    జేపీ
    1.32
     obtuse
    1.31
     paraphrase
    1.30
     tämän
    1.27
    ないので
    1.27
     الَّذ
    1.26
    鵑
    1.25
    POSITIVE LOGITS
    i
    1.68
    iiv
    1.47
    ना
    1.43
    starch
    1.38
    some
    1.37
    lists
    1.36
    碰
    1.31
    irittura
    1.31
    tiin
    1.31
    ीत
    1.31
    Act Density 0.002%

    No Known Activations