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

    Neuronpedia

    INDEX
    Explanations

    model

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     unstoppable
    -0.08
    קרב
    -0.08
    趱
    -0.07
    精准
    -0.07
     SEO
    -0.07
    .Resolve
    -0.07
    _RD
    -0.07
    加固
    -0.07
    mare
    -0.07
    ארג
    -0.07
    POSITIVE LOGITS
     показ
    0.07
    countries
    0.07
    $x
    0.07
    uga
    0.07
    Ⓒ
    0.06
     tieten
    0.06
    lying
    0.06
    pięt
    0.06
    兒童
    0.06
    rellas
    0.06
    Act Density 0.022%

    No Known Activations