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

    Neuronpedia

    INDEX
    Explanations

    abolic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Plate
    -0.07
    (var
    -0.06
    ）。↵↵
    -0.06
    ैग
    -0.06
     Pictures
    -0.06
    \Factory
    -0.06
     kingdom
    -0.06
    ýš
    -0.06
     Termin
    -0.06
    iu
    -0.06
    POSITIVE LOGITS
    abolic
    0.13
    raph
    0.09
    fm
    0.08
    .access
    0.07
     baker
    0.06
     internationally
    0.06
     bekom
    0.06
    graph
    0.06
     disg
    0.06
    _RESERVED
    0.06
    Act Density 0.002%

    No Known Activations