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

    Neuronpedia

    INDEX
    Explanations

    nature of things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Graduate
    0.47
     conducteur
    0.44
    дым
    0.44
    এখন
    0.42
    า
    0.42
     දැන්
    0.42
     PREVENTION
    0.41
    )¶
    0.41
     громадян
    0.41
     вла
    0.40
    POSITIVE LOGITS
    /
    0.45
     bamboo
    0.44
     suman
    0.44
     obscured
    0.43
    ceso
    0.43
    /(
    0.42
     claw
    0.42
     snappy
    0.41
    ionicons
    0.41
     fing
    0.40
    Act Density 0.007%

    No Known Activations