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

    Neuronpedia

    INDEX
    Explanations

    And

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Trim
    -0.07
     між
    -0.07
     disappearance
    -0.06
    нию
    -0.06
     advantageous
    -0.06
    utedString
    -0.06
     succeeded
    -0.06
     circumstance
    -0.06
     vot
    -0.06
    意见
    -0.06
    POSITIVE LOGITS
    كر
    0.06
    (urls
    0.06
    лика
    0.06
     Edmund
    0.06
    (inflater
    0.06
    setVisibility
    0.06
    Immutable
    0.06
    .HTML
    0.06
    .Abstract
    0.06
     म
    0.06
    Act Density 0.001%

    No Known Activations