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

    Neuronpedia

    INDEX
    Explanations

    foreign

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Combo
    -0.07
     berry
    -0.07
    _pa
    -0.07
    lash
    -0.06
    shell
    -0.06
    ./
    -0.06
     đẹp
    -0.06
    _prob
    -0.06
     looming
    -0.06
    FullScreen
    -0.06
    POSITIVE LOGITS
     sparing
    0.07
     Foundations
    0.06
     Raises
    0.06
    那个
    0.06
     acces
    0.06
    _agents
    0.06
    /messages
    0.06
    SACTION
    0.06
     sok
    0.06
    ,Y
    0.06
    Act Density 0.005%

    No Known Activations