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

    Neuronpedia

    INDEX
    Explanations

    programming-related syntax and elements

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

    Code-related abbreviations

    np_acts-logits-general · gemini-2.0-flash

    `tr` then `e` or `a` or `i`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ondissement
    -0.72
     FIRM
    -0.53
    Życiorys
    -0.52
     firm
    -0.52
    OOTDTY
    -0.50
    Ϣ
    -0.47
    Firm
    -0.47
    prnewswire
    -0.47
    Mirrors
    -0.46
     Firm
    -0.46
    POSITIVE LOGITS
    ransition
    0.68
    rans
    0.65
    eam
    0.63
    rigger
    0.59
    arget
    0.59
    wo
    0.58
    rust
    0.58
    iming
    0.58
    ree
    0.58
    ask
    0.57
    Act Density 0.306%

    No Known Activations