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

    Neuronpedia

    INDEX
    Explanations

    list items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Kader
    0.92
    年以上
    0.91
     ยัง
    0.91
    Chk
    0.89
     otros
    0.87
    Izq
    0.87
    amatan
    0.86
    Kp
    0.86
     adicionales
    0.84
    Cmd
    0.84
    POSITIVE LOGITS
    ца
    0.80
    та
    0.71
    சே
    0.67
    о
    0.67
     PowerPoint
    0.67
     tailored
    0.66
     deserunt
    0.66
    ҳо
    0.65
    三菱
    0.64
     monologue
    0.63
    Act Density 0.000%

    No Known Activations