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
    (pro
    -0.07
    .fore
    -0.07
    ,[],
    -0.07
     Msg
    -0.07
     с
    -0.07
    emsp
    -0.07
    (note
    -0.07
     realized
    -0.06
     liên
    -0.06
    eği
    -0.06
    POSITIVE LOGITS
     setPassword
    0.06
     decisive
    0.06
     cricket
    0.06
     جریان
    0.06
    чен
    0.06
     fitting
    0.06
    ریق
    0.06
     Rally
    0.06
     현대
    0.06
     истор
    0.06
    Act Density 0.106%

    No Known Activations