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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    HV
    -0.07
    дом
    -0.06
    roy
    -0.06
    _NB
    -0.06
     Zug
    -0.06
    uento
    -0.06
     Such
    -0.06
    }</
    -0.05
    tridge
    -0.05
     glEnd
    -0.05
    POSITIVE LOGITS
    (pre
    0.07
    /google
    0.07
    。他
    0.06
    	background
    0.06
    Leaders
    0.06
     (
↵
    0.06
    ी।↵
    0.06
    ------------------------------------------------------------------------------------------------
    0.06
    .semantic
    0.06
     Jeff
    0.06
    Act Density 0.519%

    No Known Activations