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

    Neuronpedia

    INDEX
    Explanations

    sports teams

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     interacting
    -0.07
     coleg
    -0.07
    دارة
    -0.07
    Detection
    -0.06
     Modeling
    -0.06
     revolutions
    -0.06
    .monitor
    -0.06
     playful
    -0.06
     tanto
    -0.06
    .Location
    -0.06
    POSITIVE LOGITS
    ンピ
    0.06
     assh
    0.06
    언
    0.06
    ρει
    0.06
    	ans
    0.06
    �
    0.06
    imde
    0.06
    婚
    0.06
    �
    0.05
    füg
    0.05
    Act Density 0.014%

    No Known Activations