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

    Neuronpedia

    INDEX
    Explanations

    unter- prefix

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    y
    -0.11
    wards
    -0.10
    rai
    -0.10
     Todd
    -0.09
    udas
    -0.09
    ed
    -0.09
    нÑıÑĤи
    -0.09
    istrovstvÃŃ
    -0.09
     vast
    -0.09
    raith
    -0.09
    POSITIVE LOGITS
    пÑĢиÑĶм
    0.10
    repr
    0.10
    tit
    0.10
    oreach
    0.10
     ander
    0.10
    ird
    0.09
    minated
    0.09
    chied
    0.09
    neath
    0.09
    vens
    0.09
    Act Density 0.021%

    No Known Activations