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

    Neuronpedia

    INDEX
    Explanations

    ellipses and spread operators in code

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

    object spreading and variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     enfans
    -0.73
     queſta
    -0.66
     feroit
    -0.63
     Infór
    -0.62
     auroit
    -0.61
     miniaturka
    -0.59
     Wikiseite
    -0.56
     pouvoit
    -0.55
     étoient
    -0.54
    /*
    -0.53
    POSITIVE LOGITS
     {...
    0.76
    ...
    0.75
    ([...
    0.73
     ...
    0.65
    {...
    0.63
     [...
    0.60
    ...(
    0.60
    ,...,
    0.57
    ...,
    0.54
    putAll
    0.53
    Act Density 0.003%

    No Known Activations