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

    Neuronpedia

    INDEX
    Explanations

    expressions of strong emotions and exaggerated states

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

    Extreme or hyperbolic expressions

    np_acts-logits-general · gemini-2.0-flash

    extreme states and intensity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ()?;
    -0.87
     disambiguazione
    -0.76
    migrationBuilder
    -0.74
    ANDUM
    -0.74
    AnchorStyles
    -0.72
     Pristupljeno
    -0.66
    }}}
    -0.66
    حياتها
    -0.65
    ",@"
    -0.65
    tvguidetime
    -0.64
    POSITIVE LOGITS
     literally
    0.67
     Literally
    0.67
    literally
    0.63
    Literally
    0.59
    เลย
    0.59
     imaginable
    0.59
     litté
    0.58
     literalmente
    0.56
    !!!
    0.54
    Seriously
    0.53
    Act Density 0.271%

    No Known Activations