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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     změn
    -0.06
    (EVENT
    -0.06
     GUILayout
    -0.06
    Locator
    -0.06
     เก
    -0.05
    ReLU
    -0.05
     наз
    -0.05
     DAYS
    -0.05
    971
    -0.05
     bumper
    -0.05
    POSITIVE LOGITS
     lac
    0.07
     參
    0.07
     grandmother
    0.07
     souvent
    0.06
    /at
    0.06
    ціональ
    0.06
     lit
    0.06
     jon
    0.06
     supervise
    0.06
     vit
    0.06
    Act Density 0.002%

    No Known Activations