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

    Neuronpedia

    INDEX
    Explanations

    especially conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    StillWater
    0.40
     ច
    0.40
     bactéri
    0.39
     নেতাদের
    0.38
     LEGAL
    0.38
     KUR
    0.38
     അന
    0.38
     legalize
    0.38
     craindre
    0.38
     visiteurs
    0.37
    POSITIVE LOGITS
    Scroll
    0.41
     Scroll
    0.39
     disabled
    0.39
    ˮ
    0.37
    Writer
    0.37
     disables
    0.37
    oises
    0.36
     Schmitz
    0.36
     known
    0.36
    etah
    0.36
    Act Density 0.000%

    No Known Activations