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

    Neuronpedia

    INDEX
    Explanations

    structured lists and explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     chime
    0.43
     brane
    0.41
     viewport
    0.40
     flatten
    0.39
     wavenumber
    0.38
     analyse
    0.38
     graphon
    0.38
     psychopath
    0.38
     ansatz
    0.38
     revolutionize
    0.38
    POSITIVE LOGITS
     फिलहाल
    0.40
     Easier
    0.36
    good
    0.36
    éct
    0.34
     Современ
    0.33
    おすすめです
    0.32
     GOOD
    0.32
     जल्द
    0.32
    切实
    0.32
    ara
    0.32
    Act Density 0.121%

    No Known Activations