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

    Neuronpedia

    INDEX
    Explanations

    different voices

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cần
    -0.07
     $_[
    -0.06
     find
    -0.06
     Uber
    -0.06
     Natal
    -0.06
    岁
    -0.06
     Mathematical
    -0.06
     gái
    -0.06
    acea
    -0.06
     sát
    -0.06
    POSITIVE LOGITS
    ´t
    0.08
    defs
    0.08
    _hi
    0.08
    แถ
    0.07
     trab
    0.07
     tearing
    0.07
    ٶ
    0.07
     racks
    0.07
    잿
    0.07
     yeah
    0.07
    Act Density 0.033%

    No Known Activations