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

    Neuronpedia

    INDEX
    Explanations

    habitual

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Three
    -0.07
    �
    -0.07
     실�
    -0.07
    �
    -0.06
     Corner
    -0.06
    omb
    -0.06
    因地制宜
    -0.06
    闱
    -0.06
    遴
    -0.06
    Выб
    -0.06
    POSITIVE LOGITS
    Bat
    0.08
    FragmentManager
    0.07
    に対して
    0.07
     resulted
    0.07
     Ut
    0.07
     כאלה
    0.07
     เรา
    0.07
     leider
    0.07
     Kel
    0.07
    extrême
    0.07
    Act Density 0.002%

    No Known Activations