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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ně
    -0.07
    никам
    -0.06
     Ned
    -0.06
    Php
    -0.06
    _red
    -0.06
     drummer
    -0.06
    rieving
    -0.06
     كبير
    -0.06
    minus
    -0.06
     Hew
    -0.06
    POSITIVE LOGITS
     adjustable
    0.06
    &,
    0.06
    уз
    0.06
    !!!↵↵
    0.06
    DATE
    0.06
    이었다
    0.06
    Ask
    0.06
    jourd
    0.06
     Collect
    0.06
     fflush
    0.06
    Act Density 0.000%

    No Known Activations