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

    Neuronpedia

    INDEX
    Explanations

    coding functions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Vit
    -0.06
    ós
    -0.06
    form
    -0.06
    Mana
    -0.06
     headlines
    -0.06
    ——
    -0.06
    WithValue
    -0.06
    embedded
    -0.06
    Ros
    -0.06
     weit
    -0.06
    POSITIVE LOGITS
    oulos
    0.07
    ・ア
    0.07
     projekt
    0.07
    Experts
    0.06
     комму
    0.06
    Gu
    0.06
    atı
    0.06
     Germany
    0.06
    ยนตร
    0.06
    (alias
    0.06
    Act Density 0.027%

    No Known Activations