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

    Neuronpedia

    INDEX
    Explanations

    your browsing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     horn
    0.47
     horns
    0.45
     mine
    0.43
     bolder
    0.43
     gay
    0.43
     reports
    0.41
     qualit
    0.41
     espectáculo
    0.40
     quotes
    0.40
     backs
    0.40
    POSITIVE LOGITS
     உட்பட
    0.43
     направления
    0.39
    wezig
    0.39
    zaXRvcn
    0.39
    🙋
    0.38
     ഇവിടെ
    0.38
     Hòa
    0.38
     অনুপস্থিত
    0.38
     ثلاث
    0.37
    щён
    0.37
    Act Density 0.000%

    No Known Activations