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

    Neuronpedia

    INDEX
    Explanations

    ridiculous and ridiculing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    STAR
    0.92
    再去
    0.80
    ෙන්ම
    0.80
     magnes
    0.80
     interst
    0.79
    stars
    0.79
    ente
    0.78
    rike
    0.78
    hits
    0.75
    star
    0.73
    POSITIVE LOGITS
    ਿੰ
    0.75
    ván
    0.75
    িং
    0.69
     tượng
    0.68
     denoting
    0.68
     den
    0.68
    济
    0.67
    ículo
    0.66
     ih
    0.65
    quée
    0.65
    Act Density 0.008%

    No Known Activations