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

    Neuronpedia

    INDEX
    Explanations

    pick up

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     lathe
    0.76
    Kako
    0.75
     koş
    0.75
     Barra
    0.74
    smiley
    0.74
    וריה
    0.71
    冏
    0.71
     laik
    0.70
    scoreboard
    0.69
    वेलकम
    0.69
    POSITIVE LOGITS
    pocket
    1.55
    axe
    1.22
     pockets
    1.09
    eted
    1.08
     pocket
    1.07
    eting
    1.05
    Pocket
    1.00
     up
    0.99
    nick
    0.97
     apart
    0.96
    Act Density 0.079%

    No Known Activations