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

    Neuronpedia

    INDEX
    Explanations

    say "u" words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     overseas
    -0.07
    Summary
    -0.06
     students
    -0.06
    ere
    -0.06
     wave
    -0.06
    érique
    -0.06
    所以
    -0.06
    ienen
    -0.06
    Printing
    -0.06
     tattoo
    -0.06
    POSITIVE LOGITS
     ответствен
    0.07
     Duterte
    0.06
    egal
    0.06
     Ödül
    0.06
     Marion
    0.06
    081
    0.06
     chiar
    0.06
    .Nav
    0.06
    antom
    0.06
     microtime
    0.06
    Act Density 0.004%

    No Known Activations