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

    Neuronpedia

    INDEX
    Explanations

    phrases that involve looking or noticing something

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

    look, inspect, and wait

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Italijani
    -0.51
    sweise
    -0.48
    Ӕ
    -0.42
     Grüßen
    -0.40
    Groeten
    -0.40
    SourceChecksum
    -0.39
     Roskov
    -0.39
     budeme
    -0.38
     Мексичка
    -0.38
     Grüsse
    -0.36
    POSITIVE LOGITS
    出版年
    0.63
    expandindo
    0.54
    IntoConstraints
    0.51
    rictive
    0.49
    InputBorder
    0.48
     GenerationType
    0.48
    NonNull
    0.48
    TargetApi
    0.47
    breath
    0.45
    PointerException
    0.45
    Act Density 0.008%

    No Known Activations