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

    Neuronpedia

    INDEX
    Explanations

    was

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     NST
    -0.07
     pc
    -0.07
     QT
    -0.07
     danske
    -0.07
     LSB
    -0.07
    .std
    -0.06
     نماز
    -0.06
     регі
    -0.06
     fflush
    -0.06
    NST
    -0.06
    POSITIVE LOGITS
     gotten
    0.07
     translated
    0.07
    ories
    0.07
    obby
    0.07
    vice
    0.07
    abile
    0.06
     own
    0.06
     apply
    0.06
     Initialize
    0.06
    )}>↵
    0.06
    Act Density 0.000%

    No Known Activations