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

    Neuronpedia

    INDEX
    Explanations

    return none or empty tensor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    0.36
    ↵↵
    0.34
    f
    0.33
    which
    0.32
    ل
    0.31
    k
    0.30
    With
    0.30
    。
    0.30
    I
    0.30
     vilket
    0.29
    POSITIVE LOGITS
     &/
    0.39
    ড়ান্ত
    0.38
    0.35
     insurmountable
    0.35
     अथवा
    0.35
     অথবা
    0.34
     ಅಥವಾ
    0.34
     Primeiro
    0.34
    0.33
     our
    0.33
    Act Density 0.002%

    No Known Activations