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

    Neuronpedia

    INDEX
    Explanations

    white

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Podcast
    -0.07
     vực
    -0.07
     işlet
    -0.07
    ोषण
    -0.06
     bergen
    -0.06
     giden
    -0.06
    _reservation
    -0.06
     verilm
    -0.06
    ervas
    -0.06
     breakdown
    -0.06
    POSITIVE LOGITS
    (inner
    0.07
    tical
    0.07
    ulatory
    0.07
     grandmother
    0.06
     VIA
    0.06
     Corn
    0.06
    cene
    0.06
    .Core
    0.06
    nation
    0.06
    sects
    0.06
    Act Density 0.007%

    No Known Activations