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

    Neuronpedia

    INDEX
    Explanations

    da

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    興
    -0.08
    楙
    -0.07
    ;};↵
    -0.07
    _win
    -0.07
    .ContentAlignment
    -0.07
    🐥
    -0.07
    ఆ
    -0.07
     terminates
    -0.07
     tea
    -0.07
     усл
    -0.07
    POSITIVE LOGITS
    �자
    0.09
    aille
    0.08
    odable
    0.07
    izione
    0.07
    -feature
    0.07
    iedade
    0.07
    раниц
    0.07
     randomly
    0.07
     wolves
    0.07
    ('@/
    0.07
    Act Density 0.008%

    No Known Activations