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

    Neuronpedia

    INDEX
    Explanations

    Citations/References in scientific texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Towards
    -0.07
    Better
    -0.07
    被动
    -0.07
    比べ
    -0.07
    𝛿
    -0.07
    $,
    -0.07
    泃
    -0.07
    暧昧
    -0.06
     considered
    -0.06
     adjusted
    -0.06
    POSITIVE LOGITS
     smash
    0.08
    /{}/
    0.07
    ♪
    0.07
    部落
    0.07
    Mounted
    0.07
    벳
    0.07
     getInt
    0.07
    坚实的
    0.07
    📥
    0.07
    prar
    0.07
    Act Density 0.034%

    No Known Activations