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

    Neuronpedia

    INDEX
    Explanations

    compound noun phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ą
    0.60
    Sono
    0.55
    在
    0.54
    मध्ये
    0.53
     internacional
    0.53
    আ
    0.53
    ør
    0.52
    1
    0.52
    נים
    0.52
    (
    0.52
    POSITIVE LOGITS
     AcOH
    0.61
     KFC
    0.58
     NPCs
    0.57
     ditth
    0.57
     योर
    0.56
     DSLR
    0.55
     الرح
    0.55
     parsley
    0.54
     nChar
    0.54
    <unused2179>
    0.54
    Act Density 0.018%

    No Known Activations