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

    Neuronpedia

    INDEX
    Explanations

    processes and steps involved in methodologies or instructions

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

    progression or gradual change

    np_acts-logits-general · gemini-2.0-flash

    gradual successive steps

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Taktlose
    -0.56
    stdc
    -0.55
     الحره
    -0.53
     referrerpolicy
    -0.52
    hyrchwyd
    -0.52
     lenker
    -0.50
    ioutil
    -0.50
    RuleContext
    -0.48
    saraba
    -0.47
    migrationBuilder
    -0.46
    POSITIVE LOGITS
     successive
    0.71
     progressive
    0.71
     sequentially
    0.70
     progressively
    0.69
     stages
    0.69
     progres
    0.69
     progression
    0.68
     steps
    0.68
     gradually
    0.67
     gradual
    0.66
    Act Density 0.918%

    No Known Activations