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

    Neuronpedia

    INDEX
    Explanations

    Compat

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    目の
    -0.07
     beginner
    -0.07
    fieldset
    -0.07
    ʕ
    -0.07
     gst
    -0.07
     kullanıcı
    -0.07
     برنامج
    -0.07
     dumb
    -0.07
     zen
    -0.07
    舌尖
    -0.07
    POSITIVE LOGITS
    thetic
    0.08
    밧
    0.07
     Il
    0.07
     offered
    0.07
     ret
    0.07
    חת
    0.07
    ociety
    0.07
    ali
    0.07
    ...')↵
    0.06
    onne
    0.06
    Act Density 0.001%

    No Known Activations