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

    Neuronpedia

    INDEX
    Explanations

    body size, rock wall

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tahu
    0.49
    ުގައި
    0.44
     знаете
    0.43
     знают
    0.43
    နည်း
    0.41
    Jac
    0.40
     know
    0.40
    για
    0.39
     जानता
    0.39
    ్వ
    0.38
    POSITIVE LOGITS
     جبر
    0.41
    け
    0.40
    ིས་
    0.38
     COMPENSATION
    0.38
    涨
    0.38
    िती
    0.38
     출시
    0.38
    扩张
    0.37
     перспек
    0.36
     ));
    0.36
    Act Density 0.001%

    No Known Activations