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

    Neuronpedia

    INDEX
    Explanations

    terms related to statistical analysis and baseline measurements

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

    the start or beginning of something

    np_acts-logits-general · gemini-2.0-flash

    beginning, initial, opening, baseline

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    findpost
    -0.59
    specialchars
    -0.55
     finally
    -0.54
    argout
    -0.53
    jsdelivr
    -0.46
    herokuapp
    -0.46
    urlencoded
    -0.45
     popular
    -0.45
     ex
    -0.45
    ритори
    -0.44
    POSITIVE LOGITS
     iniziale
    1.13
     inicial
    1.00
     beginnings
    0.90
     initiale
    0.88
    initial
    0.87
     Inicial
    0.86
     initializes
    0.86
    Initial
    0.85
     INITIAL
    0.85
     Starting
    0.84
    Act Density 0.690%

    No Known Activations