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

    Neuronpedia

    INDEX
    Explanations

    Names and titles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     crews
    -0.07
    �자
    -0.07
     силу
    -0.07
     nn
    -0.07
    cho
    -0.07
    preced
    -0.06
     bears
    -0.06
    ventario
    -0.06
    ال
    -0.06
     doom
    -0.06
    POSITIVE LOGITS
    _binary
    0.07
     Legal
    0.06
     Integr
    0.06
    /local
    0.06
     Melbourne
    0.06
     Presidents
    0.06
     Venice
    0.06
    iena
    0.06
     تنظیم
    0.06
    executable
    0.06
    Act Density 0.061%

    No Known Activations