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

    Neuronpedia

    INDEX
    Explanations

    ations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    、お
    -0.07
     climates
    -0.07
     pstmt
    -0.06
    146
    -0.06
     hbox
    -0.06
     ag
    -0.06
     آینده
    -0.06
     multiplying
    -0.06
    WO
    -0.06
     statement
    -0.06
    POSITIVE LOGITS
     alterations
    0.11
     aberr
    0.09
    ations
    0.09
    mercial
    0.08
    -of
    0.07
    τικές
    0.07
    SOEVER
    0.07
     resh
    0.06
     Бер
    0.06
     direkt
    0.06
    Act Density 0.005%

    No Known Activations