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

    Neuronpedia

    INDEX
    Explanations

    code closing punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    This
    0.87
    Vill
    0.80
     This
    0.79
    Longrightarrow
    0.76
    criptions
    0.74
     लिहाज
    0.72
    innon
    0.71
    माणे
    0.70
    geht
    0.69
     vill
    0.69
    POSITIVE LOGITS
    )}
    0.70
    }).
    0.69
     zub
    0.67
    थर
    0.66
     let
    0.64
     கூடாது
    0.64
    }`
    0.63
    -(-
    0.63
     लू
    0.63
    }.}
    0.63
    Act Density 0.044%

    No Known Activations