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

    Neuronpedia

    INDEX
    Explanations

    names introduced by "by"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ethoven
    0.81
    players
    0.74
     মন্ত্রণালয়
    0.74
    istry
    0.74
    ifiers
    0.73
    personas
    0.73
    Presets
    0.73
     मोदी
    0.72
    hato
    0.72
    ermen
    0.71
    POSITIVE LOGITS
     journalist
    2.00
     novelist
    1.99
     businessman
    1.92
     writer
    1.79
     comedian
    1.78
     filmmaker
    1.77
     mathematician
    1.75
     songwriter
    1.74
     anthropologist
    1.73
     physicist
    1.72
    Act Density 0.056%

    No Known Activations