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

    Neuronpedia

    INDEX
    Explanations

    internal temperature

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    그
    0.57
    ب
    0.56
    0.51
    ین
    0.50
    ف
    0.47
    जे
    0.47
    Benzo
    0.47
    ह
    0.46
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.45
    𝗟
    0.45
    POSITIVE LOGITS
     Herstellung
    0.57
     dienst
    0.55
     Anlage
    0.55
    zahl
    0.54
     zullen
    0.54
     Werte
    0.54
     Zou
    0.53
     ശക്ത
    0.53
    essä
    0.52
     gestalten
    0.52
    Act Density 0.000%

    No Known Activations