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

    Neuronpedia

    INDEX
    Explanations

    rational justification, zero liquid discharge, yticks, tracking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    és
    0.54
    itió
    0.51
    ifié
    0.50
    "
    0.50
    acking
    0.49
    té
    0.48
    ையால்
    0.48
    <0x84>
    0.48
    abilité
    0.48
    onomie
    0.47
    POSITIVE LOGITS
    ква
    0.53
     salicylate
    0.48
     sew
    0.46
    getImage
    0.46
     magní
    0.46
     hydrogenation
    0.45
     putri
    0.45
     pesca
    0.45
     mercury
    0.44
     senjata
    0.44
    Act Density 0.000%

    No Known Activations