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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     مخروط
    -0.07
    unbind
    -0.06
    �
    -0.06
     збір
    -0.06
    Winvalid
    -0.06
    (y
    -0.06
    shortcut
    -0.06
     ήταν
    -0.06
    -www
    -0.06
     SWAT
    -0.06
    POSITIVE LOGITS
     Osaka
    0.07
    hv
    0.07
    _episodes
    0.07
     amor
    0.06
    _DEPTH
    0.06
    amoto
    0.06
     bb
    0.06
     페이지
    0.06
    大的
    0.06
    midt
    0.06
    Act Density 0.054%

    No Known Activations