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

    Neuronpedia

    INDEX
    Explanations

    hurt

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     conseg
    -0.07
     lắp
    -0.07
     offre
    -0.07
     ejemplo
    -0.07
     века
    -0.06
    atio
    -0.06
     defa
    -0.06
     широк
    -0.06
     Bride
    -0.06
     číslo
    -0.06
    POSITIVE LOGITS
     hurt
    0.17
     hurts
    0.15
     hurting
    0.14
     Hurt
    0.12
     Hur
    0.09
    Hur
    0.08
    urt
    0.08
     RectTransform
    0.08
     gunshot
    0.07
     harm
    0.07
    Act Density 0.008%

    No Known Activations