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

    Neuronpedia

    INDEX
    Explanations

    into

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     eliminate
    -0.07
    -Y
    -0.06
     виб
    -0.06
     complementary
    -0.06
     sĩ
    -0.06
     Restrictions
    -0.06
    عاد
    -0.06
     cylinder
    -0.06
    hrs
    -0.06
     frei
    -0.06
    POSITIVE LOGITS
    anic
    0.06
     dabei
    0.06
     chave
    0.06
    sh
    0.06
    PUT
    0.06
    UIImageView
    0.06
    uracion
    0.06
    emain
    0.06
    put
    0.06
    expire
    0.06
    Act Density 0.228%

    No Known Activations