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

    Neuronpedia

    INDEX
    Explanations

    chan

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     recur
    -0.07
     bird
    -0.07
    zí
    -0.07
    ].[
    -0.07
     veri
    -0.07
    敌
    -0.06
     agregar
    -0.06
     люб
    -0.06
     Pix
    -0.06
     earnings
    -0.06
    POSITIVE LOGITS
     openid
    0.07
     فول
    0.06
    ¬
    0.06
    Hopefully
    0.06
     HttpServletResponse
    0.06
     beep
    0.06
     dishwasher
    0.06
    .jp
    0.06
    ||↵
    0.06
    蔵
    0.06
    Act Density 0.001%

    No Known Activations