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

    Neuronpedia

    INDEX
    Explanations

    the presence of dimensions or measurement terms related to size and scale

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

    scale by number

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AISSEE
    -0.46
     besluit
    -0.45
     dezelve
    -0.44
     pouvoit
    -0.44
     peuples
    -0.44
    cloudflare
    -0.43
    OCCURRED
    -0.43
     Inscrivez
    -0.43
    strerror
    -0.42
    étoit
    -0.41
    POSITIVE LOGITS
    Twice
    0.92
     Twice
    0.84
     twice
    0.83
    twice
    0.80
     double
    0.70
     thrice
    0.69
     TWICE
    0.63
    Double
    0.62
     zweimal
    0.62
     Double
    0.59
    Act Density 0.155%

    No Known Activations