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

    Neuronpedia

    INDEX
    Explanations

    phone

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     diketahui
    -0.10
     tendo
    -0.08
     beloved
    -0.08
     locomotive
    -0.08
     tempered
    -0.08
     مم
    -0.08
     puder
    -0.08
    uder
    -0.08
     Zucker
    -0.07
     strolling
    -0.07
    POSITIVE LOGITS
     المحمول
    0.12
     телефона
    0.09
    phones
    0.08
    /mobile
    0.08
    inals
    0.08
    铃
    0.08
    Disconnected
    0.08
    上的
    0.08
    /email
    0.08
    _AC
    0.07
    Act Density 0.023%

    No Known Activations