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

    Neuronpedia

    INDEX
    Explanations

    end punctuation in sentences

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

    Code-related tokens or first letters in a sequence

    np_acts-logits-general · gemini-2.0-flash

    time expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    saraba
    -0.92
    tvguidetime
    -0.82
    ftagPool
    -0.82
     CreateTagHelper
    -0.82
    DebuggerNonUser
    -0.79
    ✨:
    -0.79
     pinulongan
    -0.78
     zelfs
    -0.76
     EconPapers
    -0.76
    تقاوى
    -0.74
    POSITIVE LOGITS
     Later
    0.95
    Later
    0.93
     soon
    0.86
     later
    0.85
    Meanwhile
    0.84
    After
    0.83
     Soon
    0.82
     days
    0.80
    Soon
    0.80
    later
    0.80
    Act Density 0.193%

    No Known Activations