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

    Neuronpedia

    INDEX
    Explanations

    punctuation and code structure within programming language syntax

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

    control words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :+:
    -0.46
     дописавши
    -0.44
     resourceCulture
    -0.43
    marginHorizontal
    -0.41
    ={`/
    -0.41
     $[\
    -0.40
     IndexPath
    -0.40
     YEARS
    -0.40
    toPromise
    -0.39
     AÑOS
    -0.38
    POSITIVE LOGITS
     Controls
    0.70
     Control
    0.69
    controls
    0.68
    control
    0.66
    Controls
    0.64
     control
    0.63
    Control
    0.61
     Controlled
    0.61
    ontrol
    0.60
    Controlled
    0.59
    Act Density 0.003%

    No Known Activations