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

    Neuronpedia

    INDEX
    Explanations

    use

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    174
    -0.07
    migration
    -0.06
     Islamabad
    -0.06
     sparing
    -0.06
     autob
    -0.06
    oglob
    -0.06
     breakout
    -0.06
    _literals
    -0.06
    LLLL
    -0.06
    nten
    -0.06
    POSITIVE LOGITS
     gunfire
    0.07
     vacancy
    0.07
     معت
    0.06
     Serializer
    0.06
    404
    0.06
     GetUser
    0.06
     stir
    0.06
    .xml
    0.06
    _device
    0.06
    .GetUser
    0.06
    Act Density 0.010%

    No Known Activations