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

    Neuronpedia

    INDEX
    Explanations

    percentages and data parameters in a technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    graph syntax delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     незавершена
    -0.70
    LookAnd
    -0.68
     ब्रेकडाउन
    -0.65
    RTSN
    -0.62
    AsUp
    -0.60
    ⟬
    -0.60
     increí
    -0.59
    MLLoader
    -0.59
    Jeografia
    -0.59
     Infór
    -0.57
    POSITIVE LOGITS
    _
    0.42
     
    0.37
    WEBPACK
    0.35
    3
    0.33
    1
    0.33
    V
    0.33
     Jared
    0.32
     Virology
    0.32
    ❋
    0.31
    <<<<<<<
    0.30
    Act Density 0.001%

    No Known Activations