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

    Neuronpedia

    INDEX
    Explanations

    command prompts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ເພດ
    0.46
     cyclin
    0.43
     있었다
    0.42
    Played
    0.42
     세포
    0.41
     했다
    0.41
     jugó
    0.41
     déchets
    0.41
    кты
    0.40
    enfant
    0.40
    POSITIVE LOGITS
     Let
    0.48
     MK
    0.47
     Is
    0.46
     Please
    0.46
     Mk
    0.45
     Set
    0.44
     please
    0.43
     Get
    0.43
     Take
    0.43
     Raj
    0.42
    Act Density 0.080%

    No Known Activations