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

    Neuronpedia

    INDEX
    Explanations

    references to data structures and their properties in code

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

    Refers to the first item or element

    np_acts-logits-general · gemini-2.0-flash

    first, left, right, numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    帖最后由
    -0.66
     ujednoznacz
    -0.59
    [::-
    -0.53
    SequentialGroup
    -0.52
     nakalista
    -0.52
    __":
    -0.52
     complicated
    -0.50
    Epil
    -0.50
     unknownFields
    -0.49
     tiện
    -0.49
    POSITIVE LOGITS
     first
    0.78
     första
    0.75
    first
    0.73
     firſt
    0.69
    JsonPropertyName
    0.69
    enterOuterAlt
    0.67
     primera
    0.66
    第一个
    0.65
     izquierdo
    0.65
     ersten
    0.65
    Act Density 0.581%

    No Known Activations