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

    Neuronpedia

    INDEX
    Explanations

    audience

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    eh
    -0.07
    Mut
    -0.07
     Rebellion
    -0.06
     مالی
    -0.06
     repeatedly
    -0.06
    热
    -0.06
    -feature
    -0.06
     HinderedRotor
    -0.06
    篇
    -0.06
    -orange
    -0.06
    POSITIVE LOGITS
     log
    0.07
     sürdür
    0.07
    <div
    0.07
    ('.')↵
    0.07
     cherche
    0.06
    شمالی
    0.06
     🙂↵↵
    0.06
    usher
    0.06
     legitimately
    0.06
     MIC
    0.06
    Act Density 0.035%

    No Known Activations