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

    Neuronpedia

    INDEX
    Explanations

    hard

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Expires
    -0.09
    .getBounds
    -0.08
    蓢
    -0.08
    .sendKeys
    -0.07
    _ioctl
    -0.07
    ibt
    -0.07
    逍遥
    -0.07
    ď
    -0.07
    .robot
    -0.07
    disposing
    -0.07
    POSITIVE LOGITS
     GU
    0.07
     charm
    0.07
     hern
    0.07
     Interfaces
    0.06
     pregnancies
    0.06
     tatto
    0.06
    _REV
    0.06
     narrower
    0.06
    强迫
    0.06
     MEN
    0.06
    Act Density 0.029%

    No Known Activations