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

    Neuronpedia

    INDEX
    Explanations

    discussing career trajectories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ناوی
    0.53
     Гинд
    0.51
    SHOT
    0.48
    BOSE
    0.47
    DrvGPIO
    0.47
    苚
    0.45
     Фургала
    0.45
    御座
    0.45
    薷
    0.45
     addSubview
    0.45
    POSITIVE LOGITS
    z
    0.48
    phosph
    0.47
     cycle
    0.46
    cycle
    0.45
     cohort
    0.44
     of
    0.44
     tidligere
    0.44
     y
    0.43
    ne
    0.43
     transferring
    0.43
    Act Density 0.015%

    No Known Activations