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

    Neuronpedia

    INDEX
    Explanations

    reference markers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cage
    -0.08
     �
    -0.06
    .Does
    -0.06
    acro
    -0.06
    兩
    -0.06
     sphere
    -0.06
     cages
    -0.06
    [w
    -0.06
     Національ
    -0.06
    FolderPath
    -0.06
    POSITIVE LOGITS
    бо
    0.07
    ioso
    0.07
     حال
    0.06
    救
    0.06
    _entropy
    0.06
    ์ของ
    0.06
     intersect
    0.06
     manifesto
    0.06
    午
    0.06
    icago
    0.06
    Act Density 0.027%

    No Known Activations