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

    Neuronpedia

    INDEX
    Explanations

    ='

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /Application
    -0.07
     franch
    -0.07
     slave
    -0.06
    Contrib
    -0.06
     gauge
    -0.06
     idols
    -0.06
    Writing
    -0.06
     Pest
    -0.06
    Starting
    -0.06
     soup
    -0.06
    POSITIVE LOGITS
     undermines
    0.07
    _SIDE
    0.06
    очек
    0.06
    ="/">
    0.06
    upro
    0.06
     울
    0.06
    anske
    0.06
     темп
    0.06
    阿
    0.06
     Tay
    0.06
    Act Density 0.248%

    No Known Activations