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

    Neuronpedia

    INDEX
    Explanations

    script

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     放
    -0.08
    ження
    -0.07
    ській
    -0.07
    erglass
    -0.07
     equation
    -0.07
    атем
    -0.07
    оти
    -0.07
    OTO
    -0.06
    RICT
    -0.06
    ูช
    -0.06
    POSITIVE LOGITS
    <script
    0.08
    ovna
    0.06
    ména
    0.06
     đủ
    0.06
     мик
    0.06
     люб
    0.06
     sandals
    0.06
     Louis
    0.06
    cmds
    0.06
    下的
    0.06
    Act Density 0.004%

    No Known Activations