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

    Neuronpedia

    INDEX
    Explanations

    chickens

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Group
    -0.07
    oogle
    -0.07
    -group
    -0.07
     dài
    -0.07
     class
    -0.07
     driver
    -0.07
    الح
    -0.06
     wheels
    -0.06
    ewriter
    -0.06
     Indian
    -0.06
    POSITIVE LOGITS
    ADE
    0.06
    мини
    0.06
     republiky
    0.06
     reimburse
    0.06
    ounters
    0.06
     gridSize
    0.06
     heraus
    0.06
    room
    0.05
    Cooldown
    0.05
     　　　
    0.05
    Act Density 0.044%

    No Known Activations