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

    Neuronpedia

    INDEX
    Explanations

    saturation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    errors
    -0.07
     discuss
    -0.07
     that
    -0.07
     zoo
    -0.06
     �
    -0.06
     other
    -0.06
     Pandora
    -0.06
    (no
    -0.06
     За
    -0.06
    (console
    -0.06
    POSITIVE LOGITS
    utzt
    0.06
     getObject
    0.06
    )localObject
    0.06
    .');
    0.06
    enment
    0.06
     contours
    0.06
     Plum
    0.06
    ."""↵
    0.06
     totalement
    0.06
    _Tick
    0.05
    Act Density 0.031%

    No Known Activations