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

    Neuronpedia

    INDEX
    Explanations

    requests or applications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     blindly
    -0.07
    ias
    -0.07
     trưởng
    -0.06
    gráf
    -0.06
    OptionsItemSelected
    -0.06
    ียม
    -0.06
    仇恨
    -0.06
    President
    -0.06
    太多
    -0.06
    성을
    -0.06
    POSITIVE LOGITS
    apsible
    0.08
    生物科技
    0.07
     MSR
    0.06
    消化
    0.06
     ['-
    0.06
     encryption
    0.06
     Telescope
    0.06
    cedure
    0.06
    udit
    0.06
     lettuce
    0.06
    Act Density 0.040%

    No Known Activations