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

    Neuronpedia

    INDEX
    Explanations

    only,

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     อาจ
    0.91
    आरआई
    0.85
     hiko
    0.82
    吭
    0.81
     hanya
    0.79
     อย่า
    0.79
    ɕ
    0.79
    క్షన్
    0.77
     żad
    0.77
     通
    0.76
    POSITIVE LOGITS
    ELSE
    0.70
     covered
    0.70
     assumption
    0.69
    infinity
    0.67
     loading
    0.66
     undis
    0.66
    ભ
    0.65
     permanence
    0.65
     sustainability
    0.64
     else
    0.63
    Act Density 0.005%

    No Known Activations