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

    Neuronpedia

    INDEX
    Explanations

    dialogue

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     puppet
    -0.08
     felis
    -0.08
     biy
    -0.08
     insulating
    -0.08
     Brilliant
    -0.07
    公交
    -0.07
    _spacing
    -0.07
     bullets
    -0.07
    яване
    -0.07
    mouseover
    -0.07
    POSITIVE LOGITS
     picker
    0.12
     Modal
    0.10
    /modal
    0.09
    _picker
    0.09
    Picker
    0.09
    picker
    0.09
    ฟรี
    0.08
     한번
    0.08
    一次
    0.08
     uploader
    0.08
    Act Density 0.004%

    No Known Activations