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

    Neuronpedia

    INDEX
    Explanations

    .defineProperty

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Unt
    -0.08
    Unt
    -0.06
     considerable
    -0.06
    ilar
    -0.06
     Jeg
    -0.06
     siguiente
    -0.06
     herd
    -0.06
     일정
    -0.06
     zahl
    -0.06
     Eggs
    -0.06
    POSITIVE LOGITS
    .defineProperty
    0.09
    Sci
    0.07
    져
    0.06
    wifi
    0.06
     textbox
    0.06
    ="__
    0.06
    mon
    0.06
    BOOL
    0.06
    高清
    0.06
     murderous
    0.06
    Act Density 0.001%

    No Known Activations