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

    Neuronpedia

    INDEX
    Explanations

    phrases related to attempts or efforts to achieve something

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

    trying to do something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     defaultstate
    -0.56
    UrlResolution
    -0.55
     <<<<<<<<<<<<<<
    -0.54
    出版年
    -0.53
    /*
    -0.52
     Alembic
    -0.51
     lenker
    -0.46
    AndEndTag
    -0.46
    exitRule
    -0.46
    centralwidget
    -0.44
    POSITIVE LOGITS
     wikipagina
    0.49
     actionMode
    0.45
     duquel
    0.45
    zionalità
    0.42
     froide
    0.41
     wacht
    0.41
     zelve
    0.40
     enfans
    0.40
    argento
    0.39
    EndGlobal
    0.39
    Act Density 0.042%

    No Known Activations