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

    Neuronpedia

    INDEX
    Explanations

    virtual machine runtime

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Expansion
    -0.07
     Perspective
    -0.07
     patriotism
    -0.07
    恺
    -0.07
     Rams
    -0.07
    蘇
    -0.07
     Unters
    -0.06
    UCT
    -0.06
    ديث
    -0.06
     deceptive
    -0.06
    POSITIVE LOGITS
    şa
    0.07
    Opaque
    0.07
    歌舞
    0.07
     coz
    0.07
     aluno
    0.07
    🅚
    0.06
    棋牌
    0.06
    ivre
    0.06
    邮轮
    0.06
     Jerusalem
    0.06
    Act Density 0.039%

    No Known Activations