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

    Neuronpedia

    INDEX
    Explanations

    function calls with arguments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     حالت
    0.44
     manchmal
    0.43
    mathbb
    0.42
     profundamente
    0.41
    penas
    0.41
     wahr
    0.41
    美好的
    0.41
    playable
    0.40
    ſh
    0.40
     bahkan
    0.39
    POSITIVE LOGITS
    _:
    0.46
     with
    0.46
    with
    0.45
    With
    0.44
     of
    0.44
    для
    0.42
    for
    0.41
     עבור
    0.40
    of
    0.40
     With
    0.40
    Act Density 0.007%

    No Known Activations