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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ★★
    -0.07
     feathers
    -0.07
     depot
    -0.06
     assisted
    -0.06
    訓
    -0.06
    extended
    -0.06
     ücret
    -0.06
    相同
    -0.06
    	Session
    -0.06
     joining
    -0.06
    POSITIVE LOGITS
    (df
    0.07
     Při
    0.06
    (simp
    0.06
    Gesture
    0.06
    :href
    0.06
    _rgba
    0.06
    <style
    0.06
    toFixed
    0.06
     Align
    0.06
     Это
    0.06
    Act Density 0.185%

    No Known Activations