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

    Neuronpedia

    INDEX
    Explanations

    terms related to user credentials and data access in a programming context

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

    technical identifiers and syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <eos>
    -0.31
     Mittel
    -0.30
     putus
    -0.30
     låter
    -0.29
     cái
    -0.28
     aimed
    -0.27
    ẩn
    -0.27
    cakup
    -0.25
     Einf
    -0.25
    ...
    -0.24
    POSITIVE LOGITS
    ChildScrollView
    0.81
    AccessorTable
    0.75
    WriteBarrier
    0.73
    IndentedString
    0.66
     sumpay
    0.66
     صوتيه
    0.66
    tagext
    0.65
    MLLoader
    0.65
    WireFormatLite
    0.63
    ⓧ
    0.60
    Act Density 0.003%

    No Known Activations