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

    Neuronpedia

    INDEX
    Explanations

    configuration options

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ्स
    1.05
    Z
    0.99
     başında
    0.97
    }$,
    0.96
     ได้
    0.94
    Г
    0.94
    Е
    0.93
     เป็น
    0.93
     endroits
    0.92
    е
    0.92
    POSITIVE LOGITS
    IVITY
    1.05
     bosonic
    1.03
    oretically
    1.03
     brushless
    1.03
     hardcore
    1.02
     dehuman
    1.02
    트워크
    1.00
     forgo
    0.98
     convoluted
    0.98
     readout
    0.98
    Act Density 0.152%

    No Known Activations