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

    Neuronpedia

    INDEX
    Explanations

    code comments and instructions related to debugging or processing errors

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

    Code snippets or instructions with placeholders

    np_acts-logits-general · gemini-2.0-flash

    code placeholder here

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ValueStyle
    -0.66
     '{@
    -0.65
    rungsseite
    -0.59
     queſto
    -0.59
     كومونز
    -0.58
    ScopeManager
    -0.58
    󠀠
    -0.58
     ſuo
    -0.57
    Personensuche
    -0.56
     TextAppearance
    -0.56
    POSITIVE LOGITS
     here
    0.37
     something
    0.36
     alguno
    0.35
     coś
    0.34
     alguma
    0.34
     alguna
    0.33
     algo
    0.32
     algún
    0.31
     aquí
    0.30
    something
    0.30
    Act Density 0.191%

    No Known Activations