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

    Neuronpedia

    INDEX
    Explanations

    am

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .simps
    -0.07
    /tty
    -0.07
    _bus
    -0.07
     расс
    -0.07
    是最好的
    -0.06
     đứng
    -0.06
     Resort
    -0.06
    九十
    -0.06
    _launcher
    -0.06
    .centerX
    -0.06
    POSITIVE LOGITS
    ﺓ
    0.08
    uar
    0.07
     success
    0.07
     delta
    0.07
     },↵
    0.07
     ,
↵
    0.07
    war
    0.07
    mun
    0.07
     At
    0.07
     oa
    0.06
    Act Density 0.000%

    No Known Activations