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

    Neuronpedia

    INDEX
    Explanations

    GPT-4o

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     İng
    0.82
    FhirExtension
    0.82
     piden
    0.82
     Mbit
    0.78
     Egal
    0.78
     말미암
    0.77
     να
    0.76
     schließen
    0.75
    wych
    0.75
     уены
    0.75
    POSITIVE LOGITS
    ik
    0.74
    okinetics
    0.70
    ৩
    0.70
    á
    0.70
    op
    0.66
    при
    0.66
    ार्थ
    0.64
    ේ
    0.64
    ハ
    0.63
     তাব
    0.63
    Act Density 0.009%

    No Known Activations