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

    Neuronpedia

    INDEX
    Explanations

    psychopaths anonymous

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    」
    -0.85
    .\\
    -0.81
    』
    -0.81
    を
    -0.81
    のことを
    -0.76
    }
    -0.75
     motivations
    -0.74
    ]\\
    -0.74
    +}
    -0.74
    )$
    -0.73
    POSITIVE LOGITS
    ydın
    0.93
    낍
    0.92
    Specifies
    0.87
     automobil
    0.83
    bahar
    0.82
    giendo
    0.82
    Determine
    0.81
    orexia
    0.80
    Noter
    0.79
     Lohan
    0.79
    Act Density 0.007%

    No Known Activations