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

    Neuronpedia

    INDEX
    Explanations

    explains effect or outcome

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    傗
    0.17
    elés
    0.17
    ování
    0.17
    考虑到
    0.17
     নিজের
    0.16
    atorias
    0.16
     esigen
    0.16
    Providing
    0.16
     Curriculum
    0.16
     Detecting
    0.16
    POSITIVE LOGITS
     why
    0.18
     unequivocal
    0.17
     what
    0.17
     dysfunctional
    0.16
     whence
    0.16
     whom
    0.16
     osse
    0.15
     verko
    0.15
    why
    0.15
     crucial
    0.15
    Act Density 0.058%

    No Known Activations