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

    Neuronpedia

    INDEX
    Explanations

    goal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Middle
    -0.07
    auce
    -0.06
    资源
    -0.06
    _placement
    -0.06
    _remain
    -0.06
     kings
    -0.06
    )+'
    -0.06
    llll
    -0.06
     resilient
    -0.06
     rubbish
    -0.06
    POSITIVE LOGITS
     Manufacturer
    0.08
    (Job
    0.06
    CBD
    0.06
     双
    0.06
    (Pointer
    0.06
     tránh
    0.06
    .documentElement
    0.06
    历
    0.06
     (_)
    0.06
     hope
    0.06
    Act Density 0.028%

    No Known Activations