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

    Neuronpedia

    INDEX
    Explanations

    prefix dis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    pressed
    0.75
    pose
    0.73
    cited
    0.72
    riction
    0.71
    citing
    0.71
    hibited
    0.71
    polymer
    0.71
    boundingRect
    0.70
    ucible
    0.69
    cision
    0.68
    POSITIVE LOGITS
     dis
    0.87
     STEAM
    0.80
     STEP
    0.78
     honour
    0.75
     rather
    0.73
     tee
    0.73
     golden
    0.71
     dyd
    0.70
     Bact
    0.70
     Dis
    0.70
    Act Density 0.015%

    No Known Activations