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

    Neuronpedia

    INDEX
    Explanations

    icons and upkeep

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cancé
    0.53
     antidepress
    0.51
     médicaments
    0.46
     expériences
    0.45
     emoción
    0.45
     transonic
    0.44
     narc
    0.43
     inguinal
    0.43
     erythrocytes
    0.43
    정이
    0.43
    POSITIVE LOGITS
     William
    0.44
     leaves
    0.42
    0.42
     Curtis
    0.40
     사실
    0.40
     Julian
    0.39
    出
    0.39
    ugar
    0.38
     Cur
    0.38
    其实
    0.38
    Act Density 0.000%

    No Known Activations