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

    Neuronpedia

    INDEX
    Explanations

    providing inspiration and guidelines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     metabolism
    0.42
     conséquences
    0.40
     consecuencia
    0.39
     disobedience
    0.38
     ekonomi
    0.38
     cardiovascular
    0.37
     molecule
    0.37
     eukary
    0.36
     życiu
    0.36
     endangering
    0.36
    POSITIVE LOGITS
     inspiration
    0.64
    参考に
    0.62
     ideas
    0.60
    inspiration
    0.60
     suggestions
    0.57
     вдох
    0.56
     sugg
    0.54
     참고
    0.54
     guide
    0.54
     guidelines
    0.53
    Act Density 0.418%

    No Known Activations