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

    Neuronpedia

    INDEX
    Explanations

    msg

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ۱۲
    -0.07
    PEAT
    -0.06
    subnet
    -0.06
    982
    -0.06
     lament
    -0.06
     العديد
    -0.06
    lj
    -0.06
    І
    -0.06
     INIT
    -0.06
    -held
    -0.06
    POSITIVE LOGITS
     nowadays
    0.06
     bullied
    0.06
    )}"↵
    0.06
    .fragments
    0.06
     พระ
    0.06
    ')"↵
    0.06
     اجتماع
    0.06
     رسم
    0.06
     assemble
    0.06
     AssemblyProduct
    0.06
    Act Density 0.001%

    No Known Activations