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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     animations
    -0.06
     localization
    -0.06
    )":
    -0.06
    ]+$
    -0.06
    .NewLine
    -0.06
    ]},
    -0.06
     Xt
    -0.06
     categor
    -0.06
    ritional
    -0.06
     either
    -0.06
    POSITIVE LOGITS
    .getBlock
    0.07
     hend
    0.07
    �
    0.06
     wasted
    0.06
     ply
    0.06
    _dd
    0.06
    ucchini
    0.06
    _offset
    0.06
     kabul
    0.06
    หลาย
    0.06
    Act Density 0.004%

    No Known Activations