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

    Neuronpedia

    INDEX
    Explanations

    go imports

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    [msg
    -0.07
     pelos
    -0.07
    (iterator
    -0.07
     H�
    -0.06
    ●●●●●●●●
    -0.06
     �
    -0.06
     Builders
    -0.06
    ools
    -0.06
    �
    -0.06
    msgs
    -0.06
    POSITIVE LOGITS
     změny
    0.07
     ліс
    0.07
    loan
    0.07
    stitial
    0.07
    ossed
    0.06
    markt
    0.06
    Environmental
    0.06
     اگر
    0.06
    -stat
    0.06
     recognized
    0.06
    Act Density 0.002%

    No Known Activations