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

    Neuronpedia

    INDEX
    Explanations

    discussing bragging

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0
    0.85
    После
    0.73
    嵬
    0.73
    ０
    0.70
    История
    0.68
    行う
    0.67
    к
    0.67
    楎
    0.65
    Ⴚ
    0.65
     políticos
    0.64
    POSITIVE LOGITS
     boasted
    0.93
    ’
    0.84
     boasts
    0.81
    t
    0.78
    j
    0.78
     bragging
    0.77
     brag
    0.73
     previews
    0.73
    ट
    0.69
    SE
    0.68
    Act Density 0.002%

    No Known Activations