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
     сказав
    -0.07
    EM
    -0.07
    	no
    -0.06
     到
    -0.06
    =q
    -0.06
    _ip
    -0.06
     Ole
    -0.06
    Employee
    -0.06
     Grow
    -0.06
     også
    -0.06
    POSITIVE LOGITS
     ваш
    0.07
     прис
    0.07
     普通
    0.07
     limp
    0.06
     hydration
    0.06
    .payload
    0.06
     reactive
    0.06
    creative
    0.06
     gentlemen
    0.06
    .EventHandler
    0.06
    Act Density 0.031%

    No Known Activations