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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    $time
    -0.07
     smoked
    -0.06
    formed
    -0.06
     getVersion
    -0.06
    /P
    -0.06
     Sharia
    -0.06
     botanical
    -0.06
    лять
    -0.06
     Pied
    -0.06
     thresholds
    -0.06
    POSITIVE LOGITS
    _HIDE
    0.07
    -backend
    0.06
    -character
    0.06
    essian
    0.06
    _SYM
    0.06
     pantalla
    0.06
     『
    0.06
    _IW
    0.06
    -big
    0.06
    ặt
    0.06
    Act Density 0.050%

    No Known Activations