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

    Neuronpedia

    INDEX
    Explanations

    notifications and instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    نا
    0.69
    ها
    0.61
    א
    0.59
    ن
    0.57
    т
    0.57
    มัน
    0.56
    ک
    0.55
    عمل
    0.55
    ก
    0.55
     Alemania
    0.54
    POSITIVE LOGITS
     curbing
    0.54
     Το
    0.51
     non
    0.49
     NOTES
    0.49
     Φ
    0.49
     ambiguous
    0.49
     Σ
    0.48
     Κ
    0.48
     π
    0.48
     πο
    0.47
    Act Density 0.000%

    No Known Activations