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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /video
    -0.07
    enha
    -0.07
     startActivityForResult
    -0.07
    .RE
    -0.06
    vice
    -0.06
     типа
    -0.06
     surprises
    -0.06
     assumes
    -0.06
     viewController
    -0.06
    ализа
    -0.06
    POSITIVE LOGITS
    _hop
    0.06
    pom
    0.06
     JB
    0.06
     чор
    0.06
     checkBox
    0.06
     CJ
    0.06
     interceptor
    0.06
    .reflect
    0.06
     речов
    0.06
    �
    0.06
    Act Density 0.083%

    No Known Activations