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

    Neuronpedia

    INDEX
    Explanations

    original list, natural hair, short, mild

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    л
    0.42
    ون
    0.39
    の
    0.39
    在
    0.38
    ın
    0.37
    ла
    0.36
     ancak
    0.35
    他の
    0.34
    ال
    0.34
    きれい
    0.34
    POSITIVE LOGITS
    (
    0.39
     (
    0.31
    y
    0.31
     for
    0.30
    ET
    0.29
    PM
    0.29
    out
    0.28
    at
    0.28
    yuan
    0.28
    omen
    0.26
    Act Density 2.447%

    No Known Activations