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

    Neuronpedia

    INDEX
    Explanations

    Solutions and ratios

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     formulas
    -0.07
    Category
    -0.07
     inside
    -0.06
    经营
    -0.06
     плит
    -0.06
    황
    -0.06
    .bottom
    -0.06
    ?f
    -0.06
    ızı
    -0.06
    Interest
    -0.06
    POSITIVE LOGITS
    ("//*[@
    0.07
    ενο
    0.06
     RTP
    0.06
     Ston
    0.06
    nom
    0.06
    icios
    0.06
     discretion
    0.06
    alted
    0.06
     多
    0.06
     blockbuster
    0.06
    Act Density 0.011%

    No Known Activations