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

    Neuronpedia

    INDEX
    Explanations

    Measurement instruments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ()})↵
    -0.07
    敬
    -0.06
    条
    -0.06
     CAB
    -0.06
    copies
    -0.06
     fire
    -0.06
    	union
    -0.06
    IU
    -0.06
    ’a
    -0.06
    .fragments
    -0.06
    POSITIVE LOGITS
    .Be
    0.07
    (datetime
    0.06
    ?[
    0.06
    147
    0.06
    foon
    0.06
     tedavi
    0.06
    져
    0.06
    volution
    0.06
    deniz
    0.06
    _GRE
    0.06
    Act Density 0.041%

    No Known Activations