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

    Neuronpedia

    INDEX
    Explanations

    years

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    nému
    -0.06
    _figure
    -0.06
     poem
    -0.06
    _issue
    -0.06
     raped
    -0.06
     Wet
    -0.06
     appointment
    -0.06
    운데
    -0.06
     phối
    -0.06
    _temperature
    -0.06
    POSITIVE LOGITS
     "),↵
    0.07
    !!}↵
    0.07
     protr
    0.06
    로그
    0.06
    (""));↵
    0.06
    edis
    0.06
     Boost
    0.06
                    ↵                ↵
    0.06
     Ninja
    0.06
     Obamacare
    0.06
    Act Density 0.046%

    No Known Activations