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

    Neuronpedia

    INDEX
    Explanations

    pads of fingers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    violin
    0.16
    seq
    0.16
    Knife
    0.16
    Massage
    0.16
    Hue
    0.15
     mowing
    0.15
    S
    0.15
    Shadow
    0.15
    Songs
    0.15
    Carr
    0.15
    POSITIVE LOGITS
     repudi
    0.15
     disgruntled
    0.15
     strada
    0.15
     urges
    0.15
    んでいた
    0.15
     tellus
    0.15
     stehen
    0.14
     repulsive
    0.14
     rechaz
    0.14
     disqualify
    0.14
    Act Density 0.002%

    No Known Activations