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

    Neuronpedia

    INDEX
    Explanations

    structures and concepts related to mathematical notation and equations

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

    LaTeX code

    np_acts-logits-general · gemini-2.0-flash

    mathematical notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    脚注の使い方
    -0.85
    ')")
    -0.80
    })();
    -0.78
     nakalista
    -0.76
    '}}
    -0.75
    providedIn
    -0.74
    ');?>
    -0.74
    ')}}
    -0.71
    })`
    -0.71
    ]$}
    -0.70
    POSITIVE LOGITS
     nationaux
    0.59
     Pues
    0.58
     maux
    0.56
    vdots
    0.52
     Cæsar
    0.51
     radiate
    0.51
     candidats
    0.51
    bundet
    0.50
     collectif
    0.49
    bereitung
    0.49
    Act Density 0.260%

    No Known Activations