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

    Neuronpedia

    INDEX
    Explanations

    observations, seeing trends

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ado
    -0.07
    ni
    -0.06
     yı
    -0.06
     حين
    -0.06
    staff
    -0.06
    enarios
    -0.06
     Hz
    -0.06
    ếp
    -0.06
    地區
    -0.06
     DU
    -0.06
    POSITIVE LOGITS
    @implementation
    0.07
     kuruluş
    0.07
     archit
    0.07
    Alright
    0.07
     expo
    0.07
    Craig
    0.07
     setups
    0.06
    -Javadoc
    0.06
    (HttpContext
    0.06
    .")↵↵
    0.06
    Act Density 0.255%

    No Known Activations