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

    Neuronpedia

    INDEX
    Explanations

    loss and related concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    CONFLICT
    0.44
    وبت
    0.44
    established
    0.43
    the
    0.42
    ಾಯಿತು
    0.40
    Settl
    0.39
    these
    0.38
    Strength
    0.38
    𝕌
    0.38
    proposal
    0.38
    POSITIVE LOGITS
     incurred
    0.61
     prevention
    0.59
     incur
    0.57
    atet
    0.48
     suffered
    0.46
     Prevention
    0.46
     prevención
    0.45
     minimo
    0.43
     loos
    0.43
     payee
    0.43
    Act Density 0.012%

    No Known Activations