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

    Neuronpedia

    INDEX
    Explanations

    we

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _px
    -0.06
     discord
    -0.06
    [%
    -0.06
     lapse
    -0.06
     POLL
    -0.06
    	alpha
    -0.06
    vä
    -0.06
     Bound
    -0.06
    Bound
    -0.06
    LogFile
    -0.06
    POSITIVE LOGITS
     cargar
    0.07
    ング
    0.06
    astery
    0.06
    _mapping
    0.06
     TI
    0.06
    997
    0.06
    (Media
    0.06
    PIC
    0.06
    76
    0.06
     项
    0.06
    Act Density 0.121%

    No Known Activations