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

    Neuronpedia

    INDEX
    Explanations

    rom

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Thom
    -0.07
     DA
    -0.06
     >
↵
    -0.06
     Knock
    -0.06
     shit
    -0.06
     مز
    -0.06
     rez
    -0.06
     hazard
    -0.06
    -mouth
    -0.06
    _TXT
    -0.06
    POSITIVE LOGITS
     Couples
    0.07
    .Register
    0.06
    emplo
    0.06
    controlled
    0.06
    oulouse
    0.06
    �
    0.06
    střed
    0.06
    월까지
    0.06
    etically
    0.06
     Panda
    0.06
    Act Density 0.008%

    No Known Activations