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

    Neuronpedia

    INDEX
    Explanations

    dominant

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     "::
    -0.06
     drum
    -0.06
     beads
    -0.06
    .space
    -0.06
     enumerate
    -0.06
    MIN
    -0.06
    songs
    -0.06
     size
    -0.06
     population
    -0.06
     thoughtful
    -0.06
    POSITIVE LOGITS
    стати
    0.07
    Coder
    0.06
    otoxic
    0.06
    (dictionary
    0.06
    having
    0.06
    .uc
    0.06
    383
    0.06
     stata
    0.06
     Mercy
    0.06
    .functions
    0.06
    Act Density 0.000%

    No Known Activations