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

    Neuronpedia

    INDEX
    Explanations

    subtraction symbol

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    οι
    -0.07
    Ý
    -0.07
     soud
    -0.07
    definition
    -0.06
     cst
    -0.06
    uu
    -0.06
    ій
    -0.06
    213
    -0.06
     gé
    -0.06
    	get
    -0.06
    POSITIVE LOGITS
     ██
    0.07
    _clusters
    0.07
     volatile
    0.06
     oak
    0.06
     concerts
    0.06
     lashes
    0.06
     *)((
    0.06
    [](
    0.06
    Something
    0.06
     lingerie
    0.06
    Act Density 0.018%

    No Known Activations