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
    modifiers
    -0.07
     finished
    -0.06
     Constit
    -0.06
     contains
    -0.06
     speeches
    -0.06
    瓜
    -0.06
     prosecution
    -0.06
    馬
    -0.06
     violated
    -0.06
     flush
    -0.06
    POSITIVE LOGITS
     kone
    0.07
    	IN
    0.06
     cevap
    0.06
     Await
    0.06
    才能
    0.06
    Unt
    0.06
     VIC
    0.06
     chiropr
    0.06
    rapy
    0.06
    Merit
    0.06
    Act Density 0.022%

    No Known Activations