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

    Neuronpedia

    INDEX
    Explanations

    aim for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    uwe
    0.41
    adh
    0.40
    bewer
    0.40
    वेंट
    0.40
    emate
    0.40
     motivations
    0.39
    avelmente
    0.39
     wiring
    0.38
     Wiring
    0.38
    arpur
    0.38
    POSITIVE LOGITS
    Aim
    0.67
     aiming
    0.58
     Aim
    0.54
     aim
    0.53
    AIM
    0.50
    lessly
    0.50
     aimed
    0.49
    thest
    0.46
    گیرد
    0.44
    lessness
    0.42
    Act Density 0.005%

    No Known Activations