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

    Neuronpedia

    INDEX
    Explanations

    code, size and configuration parameters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .aspect
    -0.07
    rior
    -0.07
    actoring
    -0.07
    redict
    -0.07
    汽
    -0.06
    caffold
    -0.06
     low
    -0.06
     crappy
    -0.06
    _Password
    -0.06
    _Read
    -0.06
    POSITIVE LOGITS
    葉
    0.07
     yerinde
    0.07
    енное
    0.06
     Der
    0.06
    Rank
    0.06
     üye
    0.06
    سات
    0.06
    RGB
    0.06
    .addClass
    0.06
     čís
    0.06
    Act Density 0.039%

    No Known Activations