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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Duch
    -0.07
    ينات
    -0.07
     والن
    -0.06
    Jwt
    -0.06
    ครง
    -0.06
    _scenario
    -0.06
    clin
    -0.06
    onn
    -0.06
     objeto
    -0.06
    таки
    -0.06
    POSITIVE LOGITS
     [...]↵↵
    0.06
     ubiquitous
    0.06
    λεί
    0.06
     start
    0.06
    .'</
    0.06
    .TextChanged
    0.06
    iating
    0.06
     unwind
    0.06
    .Named
    0.06
     cap
    0.06
    Act Density 0.081%

    No Known Activations