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

    Neuronpedia

    INDEX
    Explanations

    speak

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Find
    -0.07
     glo
    -0.07
    istory
    -0.07
    acter
    -0.06
     Wid
    -0.06
     seek
    -0.06
     ό
    -0.06
    ็นต
    -0.06
     probation
    -0.06
     استاند
    -0.06
    POSITIVE LOGITS
    _tls
    0.07
     GmbH
    0.07
    _KP
    0.07
    (job
    0.07
    escaping
    0.06
    ench
    0.06
    remainder
    0.06
     ÜNİVERSİTESİ
    0.06
    leet
    0.06
    ên
    0.06
    Act Density 0.017%

    No Known Activations