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

    Neuronpedia

    INDEX
    Explanations

    negation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     thumbnails
    0.32
     specs
    0.31
     clip
    0.30
     touchpad
    0.29
     সাধারণত
    0.29
    (
    0.29
     handy
    0.29
     opal
    0.29
     gamepad
    0.28
     enchant
    0.28
    POSITIVE LOGITS
     немає
    0.37
     nadie
    0.34
    It
    0.34
     bukan
    0.34
     niemand
    0.34
     nije
    0.33
    nicht
    0.33
     değildir
    0.33
     it
    0.33
     Nobody
    0.32
    Act Density 0.718%

    No Known Activations