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

    Neuronpedia

    INDEX
    Explanations

    Code/API-related

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -bottom
    -0.08
    (fontSize
    -0.07
     questioning
    -0.07
    -transform
    -0.07
     Amend
    -0.07
    -pass
    -0.07
     epoxy
    -0.07
     proportions
    -0.07
     đứng
    -0.07
    _STATE
    -0.07
    POSITIVE LOGITS
    _guard
    0.07
    佘
    0.07
    Gun
    0.07
    衢
    0.07
    ʐ
    0.07
    �
    0.07
    Ix
    0.06
    布鲁
    0.06
    缕
    0.06
    ជ
    0.06
    Act Density 0.119%

    No Known Activations