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

    Neuronpedia

    INDEX
    Explanations

    declarations of constants in programming code

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

    variable declaration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     RIPRODUZIONE
    -0.40
    spo
    -0.36
    いかが
    -0.36
    område
    -0.35
    recrow
    -0.35
     jäsen
    -0.34
    por
    -0.34
     îles
    -0.34
     crochê
    -0.33
     Groningen
    -0.33
    POSITIVE LOGITS
     cherchés
    0.72
    ArgsConstructor
    0.68
     CanadaChoose
    0.61
     AssemblyTitle
    0.60
    GEBURTSDATUM
    0.59
     lateinit
    0.59
    yntaxException
    0.59
    }));
    0.58
    "]));
    0.57
    let
    0.57
    Act Density 0.004%

    No Known Activations