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

    Neuronpedia

    INDEX
    Explanations

    SAML code/documentation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    κ
    -0.07
    (Program
    -0.07
     Sacr
    -0.06
    转
    -0.06
    шей
    -0.06
     Extend
    -0.06
    лі
    -0.06
     reveals
    -0.06
    loader
    -0.06
    Restore
    -0.06
    POSITIVE LOGITS
    AnimationsModule
    0.06
    汽
    0.06
    chartInstance
    0.06
    navbarDropdown
    0.06
     �
    0.06
     Pet
    0.06
    тоф
    0.06
     абсолютно
    0.05
     unaffected
    0.05
    0.05
    Act Density 0.004%

    No Known Activations