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

    Neuronpedia

    INDEX
    Explanations

    abs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ↫
    -0.08
    oment
    -0.07
     lady
    -0.07
    ――
    -0.07
    얍
    -0.06
     riff
    -0.06
    (edit
    -0.06
    -off
    -0.06
    _trial
    -0.06
    ####
    -0.06
    POSITIVE LOGITS
     ABS
    0.07
     aesthetics
    0.07
     Aust
    0.07
     Voll
    0.07
    QRS
    0.07
    .sd
    0.07
    Dt
    0.07
    กฎ
    0.07
     erg
    0.06
    _substr
    0.06
    Act Density 0.015%

    No Known Activations