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

    Neuronpedia

    INDEX
    Explanations

    altering

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    facebook
    -0.07
     elast
    -0.06
    .export
    -0.06
     cannot
    -0.06
    wan
    -0.06
    liness
    -0.06
     log
    -0.06
     müzik
    -0.06
     داش
    -0.06
     LOG
    -0.06
    POSITIVE LOGITS
    ège
    0.07
     NES
    0.07
     宮
    0.07
     recipe
    0.06
    ‌
    0.06
    až
    0.06
    ガ
    0.06
    сяч
    0.06
    -Compatible
    0.06
    Expense
    0.06
    Act Density 0.027%

    No Known Activations