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

    Neuronpedia

    INDEX
    Explanations

    multi-language text fragments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ąg
    0.77
    angled
    0.76
    джу
    0.75
     ipsa
    0.68
    ोंग
    0.68
    ang
    0.67
     ponctuées
    0.66
     ricord
    0.66
    ített
    0.66
    තර
    0.66
    POSITIVE LOGITS
    չ
    0.89
     Gujar
    0.88
     compels
    0.86
     quirky
    0.86
     Exerc
    0.84
    Er
    0.82
     Пі
    0.82
     Э
    0.81
    тэй
    0.81
    نید
    0.81
    Act Density 0.000%

    No Known Activations