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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _time
    -0.07
     kernel
    -0.07
     Delegate
    -0.06
     visitor
    -0.06
    000
    -0.06
     patience
    -0.06
     refining
    -0.06
    bridge
    -0.06
    retched
    -0.06
     Netanyahu
    -0.06
    POSITIVE LOGITS
     merkezi
    0.06
    もしれない
    0.06
    eba
    0.06
    の大
    0.06
     uyum
    0.06
     alıp
    0.06
     misguided
    0.06
    และม
    0.06
    boot
    0.06
    .Mar
    0.06
    Act Density 0.068%

    No Known Activations