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

    Neuronpedia

    INDEX
    Explanations

    to blame

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Being
    0.49
    Being
    0.45
     BEING
    0.45
     वापस
    0.42
    Want
    0.42
    being
    0.41
     разли
    0.40
    而被
    0.40
    want
    0.40
     Want
    0.39
    POSITIVE LOGITS
     blamed
    0.74
     blame
    0.74
     blames
    0.55
     fundamentally
    0.53
    ying
    0.48
     principally
    0.48
     blaming
    0.47
     supposed
    0.47
     primarily
    0.47
     principalement
    0.43
    Act Density 0.004%

    No Known Activations