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

    Neuronpedia

    INDEX
    Explanations

    specific product names or branded items

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

    pairs or duality

    np_acts-logits-general · gemini-2.0-flash

    two or dual concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     BoxFit
    -0.56
    ApiModelProperty
    -0.56
    picuous
    -0.53
    ئات
    -0.52
    !("{}",
    -0.52
    sidemargin
    -0.51
    oules
    -0.51
    
    -0.51
    NewUrlParser
    -0.50
    AndEndTag
    -0.50
    POSITIVE LOGITS
     split
    1.59
     Split
    1.42
     splitting
    1.41
    Split
    1.37
    split
    1.36
     dual
    1.32
     two
    1.29
     splits
    1.28
     twins
    1.22
     twin
    1.20
    Act Density 1.777%

    No Known Activations