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

    Neuronpedia

    INDEX
    Explanations

    references to advertisements

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

    words starting with ad

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     princí
    -0.47
    éron
    -0.47
    unico
    -0.46
    unica
    -0.44
    zete
    -0.44
    Controle
    -0.43
     comples
    -0.43
    imbang
    -0.43
     ingeniería
    -0.42
     vigilancia
    -0.42
    POSITIVE LOGITS
     ad
    1.92
     Ad
    1.04
     ads
    1.02
     Ads
    0.92
    Ad
    0.91
     AD
    0.85
     Adjutant
    0.79
     advertisement
    0.78
    Ads
    0.78
     ब्रेकडाउन
    0.73
    Act Density 0.004%

    No Known Activations