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

    Neuronpedia

    INDEX
    Explanations

    Undermining

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     investigator
    -0.06
    dispatcher
    -0.06
     args
    -0.06
     Rusya
    -0.06
     preload
    -0.06
     ViewChild
    -0.06
    MASK
    -0.06
     nhánh
    -0.05
     raping
    -0.05
     *</
    -0.05
    POSITIVE LOGITS
    って
    0.07
     equation
    0.07
    没
    0.07
    irm
    0.06
     нек
    0.06
    ucción
    0.06
     metaph
    0.06
    假
    0.06
    Ub
    0.06
    索
    0.06
    Act Density 0.021%

    No Known Activations