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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     وهو
    -0.08
     rospy
    -0.07
     Cob
    -0.07
     cornerstone
    -0.07
     UserType
    -0.07
    �
    -0.07
    πί
    -0.06
     розк
    -0.06
     yanı
    -0.06
    ันน
    -0.06
    POSITIVE LOGITS
    ILLE
    0.07
    me
    0.06
    олод
    0.06
    (Api
    0.06
    ille
    0.06
     Wheeler
    0.06
    atisch
    0.06
    innie
    0.06
     demons
    0.06
    _For
    0.06
    Act Density 0.000%

    No Known Activations