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

    Neuronpedia

    INDEX
    Explanations

    name

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Violation
    -0.06
    acje
    -0.06
    Playback
    -0.06
     Denn
    -0.06
    "}}↵
    -0.06
     commentaire
    -0.06
    ople
    -0.06
    �
    -0.06
     plotted
    -0.06
    Visualization
    -0.06
    POSITIVE LOGITS
     في
    0.07
     ef
    0.06
    Matches
    0.06
     sus
    0.06
     Shields
    0.06
    vk
    0.06
    باد
    0.06
    .emptyList
    0.06
     حمل
    0.06
     puis
    0.06
    Act Density 0.015%

    No Known Activations