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

    Neuronpedia

    INDEX
    Explanations

    introducing "why"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    只想
    0.42
     plötzlich
    0.42
     వంటి
    0.41
    只好
    0.40
     പോലുള്ള
    0.40
     ఇలా
    0.40
     sudd
    0.39
     hoping
    0.39
     possa
    0.39
     Suddenly
    0.39
    POSITIVE LOGITS
    albeit
    0.64
    少なくとも
    0.63
     albeit
    0.59
     unequivocally
    0.56
     evidenced
    0.55
     причем
    0.55
     demonstrable
    0.54
     despite
    0.53
    理由
    0.52
     inescap
    0.52
    Act Density 0.194%

    No Known Activations