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

    Neuronpedia

    INDEX
    Explanations

    acronyms preceding a comma

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Switzerland
    0.48
     기타
    0.46
    אים
    0.46
    때
    0.46
     Jewels
    0.44
    ע
    0.44
    er
    0.43
    הר
    0.43
     Shri
    0.42
    ியல்
    0.42
    POSITIVE LOGITS
     of
    0.79
    of
    0.63
    ían
    0.61
     của
    0.57
     ofthe
    0.57
     të
    0.55
     på
    0.54
     étaient
    0.54
     auf
    0.53
     políticos
    0.52
    Act Density 0.011%

    No Known Activations