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

    Neuronpedia

    INDEX
    Explanations

    lost in or lose

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    orElse
    0.38
    Attack
    0.36
    正
    0.35
    addContainerGap
    0.33
    Nature
    0.33
    Toward
    0.33
    锦
    0.33
    uolo
    0.32
    かず
    0.32
    Бан
    0.32
    POSITIVE LOGITS
     lose
    0.98
     lost
    0.90
     loses
    0.88
     теря
    0.88
     izgub
    0.86
     Lose
    0.85
     losing
    0.84
     потеря
    0.83
     pierde
    0.81
     perder
    0.80
    Act Density 0.024%

    No Known Activations