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
    Roger
    -0.07
     dn
    -0.06
    -trained
    -0.06
    Verb
    -0.06
     منذ
    -0.06
     Provided
    -0.06
    ่อไป
    -0.06
     duct
    -0.06
     ファ
    -0.06
    电影
    -0.06
    POSITIVE LOGITS
     Cookbook
    0.06
    )(*
    0.06
    peer
    0.06
    ael
    0.06
    립니다
    0.06
     Kraj
    0.06
     compet
    0.06
     شهری
    0.06
     converse
    0.05
     collar
    0.05
    Act Density 0.001%

    No Known Activations