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

    Neuronpedia

    INDEX
    Explanations

    numbers and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     berapa
    0.69
    ת
    0.68
     полную
    0.68
     запре
    0.67
     sejarah
    0.66
     fresca
    0.66
     njegova
    0.66
     sama
    0.65
     देखील
    0.64
     такую
    0.64
    POSITIVE LOGITS
    $
    0.64
    Letters
    0.57
    שים
    0.56
    }
    0.55
    (
    0.53
     (
    0.53
    Callories
    0.53
    Soul
    0.51
    Mov
    0.51
    :
    0.50
    Act Density 0.000%

    No Known Activations