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

    Neuronpedia

    INDEX
    Explanations

    conf

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -level
    -0.07
    EAR
    -0.07
     York
    -0.07
    leet
    -0.06
     шаг
    -0.06
    trak
    -0.06
    York
    -0.06
    แบบ
    -0.06
     paypal
    -0.06
    (lat
    -0.06
    POSITIVE LOGITS
     conf
    0.15
    conf
    0.12
    .conf
    0.12
     Conf
    0.12
    Conf
    0.12
    CONF
    0.11
    -conf
    0.11
    _conf
    0.10
    	conf
    0.10
    (conf
    0.09
    Act Density 0.011%

    No Known Activations