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

    Neuronpedia

    INDEX
    Explanations

    Marion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     końca
    -0.07
    🌮
    -0.07
     الد
    -0.07
     Id
    -0.07
    .Year
    -0.07
    뭇
    -0.07
    elda
    -0.07
    的成功
    -0.07
    clud
    -0.07
    ël
    -0.07
    POSITIVE LOGITS
     watchdog
    0.07
     forty
    0.07
    takes
    0.07
     tabs
    0.07
     profile
    0.07
     viewer
    0.06
     Libre
    0.06
     winters
    0.06
     •
    0.06
    预报
    0.06
    Act Density 0.007%

    No Known Activations