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

    Neuronpedia

    INDEX
    Explanations

    structured data and code or configuration elements related to technology and programming

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

    Followed by capitalized words

    np_acts-logits-general · gemini-2.0-flash

    common programming keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     BALL
    -0.42
     PLAT
    -0.41
    íveis
    -0.41
     CHAR
    -0.39
     CHLOR
    -0.39
    ível
    -0.39
     TON
    -0.38
     STE
    -0.38
     QUAL
    -0.38
     GROUND
    -0.38
    POSITIVE LOGITS
     spirituale
    0.59
     termica
    0.55
     religieuses
    0.53
     umana
    0.52
     giapp
    0.52
     Armenians
    0.51
     sottile
    0.50
     russes
    0.50
     católica
    0.49
     culturelles
    0.49
    Act Density 2.557%

    No Known Activations