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

    Neuronpedia

    INDEX
    Explanations

    clear qualities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     gathering
    0.79
    ย์
    0.76
     Cheers
    0.74
    Cheers
    0.73
     Small
    0.70
    aea
    0.70
    Small
    0.70
    ต่างๆ
    0.67
     creatures
    0.65
    oeuvre
    0.64
    POSITIVE LOGITS
    ish
    1.16
     ràng
    1.13
     unambiguous
    1.10
    headed
    1.09
     denominador
    1.04
     concise
    1.04
    ifies
    1.04
     unequivocal
    1.03
    ening
    1.02
    eners
    1.01
    Act Density 0.467%

    No Known Activations