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

    Neuronpedia

    INDEX
    Explanations

    numerical counts and totals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pier
    0.43
     erinn
    0.39
     refunds
    0.37
     Refunds
    0.37
     aide
    0.36
     reimburse
    0.36
    ্যাম
    0.36
    idation
    0.35
     wounded
    0.35
     uygun
    0.35
    POSITIVE LOGITS
    成果
    0.44
     වන
    0.40
    وات
    0.40
     caused
    0.39
    aceted
    0.39
    筷
    0.38
    jev
    0.38
    jeno
    0.38
     accusations
    0.37
    udel
    0.37
    Act Density 0.000%

    No Known Activations