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

    Neuronpedia

    INDEX
    Explanations

    risk

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    \Bridge
    -0.07
    ा-
    -0.07
    ency
    -0.06
    human
    -0.06
     Slots
    -0.06
    iß
    -0.06
     구
    -0.06
     seize
    -0.06
    Moder
    -0.06
    	Node
    -0.06
    POSITIVE LOGITS
     drawer
    0.07
    ˆ
    0.07
    LocalStorage
    0.06
     Мініст
    0.06
    /lo
    0.06
    ución
    0.06
    ButtonModule
    0.06
     AIM
    0.06
    )s
    0.06
    (rad
    0.06
    Act Density 0.018%

    No Known Activations