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

    Neuronpedia

    INDEX
    Explanations

    Prepositions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	ORDER
    -0.07
     messed
    -0.06
     gee
    -0.06
    _EST
    -0.06
     Uz
    -0.06
     coming
    -0.06
    gener
    -0.06
     thereby
    -0.06
    does
    -0.06
    “As
    -0.06
    POSITIVE LOGITS
    pons
    0.07
    ขณะท
    0.07
    理由
    0.07
     ณ
    0.07
     тяжел
    0.07
    ican
    0.07
     الأمريكية
    0.07
    يكا
    0.06
    :disable
    0.06
    .press
    0.06
    Act Density 0.022%

    No Known Activations