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

    Neuronpedia

    INDEX
    Explanations

    ::

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    าฟ
    -0.07
    938
    -0.07
    (location
    -0.07
     للد
    -0.06
    <Action
    -0.06
     _{
    -0.06
    ervas
    -0.06
     ltd
    -0.06
     Task
    -0.06
    /T
    -0.06
    POSITIVE LOGITS
    PCA
    0.06
    ウェ
    0.06
     ProductService
    0.06
    θεση
    0.06
    وتی
    0.06
    _percent
    0.06
     أب
    0.06
     Hedge
    0.06
    _ATTRIBUTES
    0.06
    (ib
    0.06
    Act Density 0.003%

    No Known Activations