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

    Neuronpedia

    INDEX
    Explanations

    code and technical discussions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _broadcast
    -0.07
     Current
    -0.06
    Deep
    -0.06
    _interfaces
    -0.06
     ischem
    -0.06
    rets
    -0.06
     RCA
    -0.06
    aurants
    -0.06
    anal
    -0.06
    =min
    -0.06
    POSITIVE LOGITS
     alot
    0.07
     *\
    0.06
     mpfr
    0.06
     بالإ
    0.06
    �
    0.06
     غير
    0.06
     ideology
    0.06
    -maker
    0.06
    ọn
    0.06
    áz
    0.06
    Act Density 0.096%

    No Known Activations