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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Halloween
    -0.07
    ployment
    -0.07
    anoi
    -0.06
    Maintenance
    -0.06
     crypt
    -0.06
    next
    -0.06
     dogs
    -0.06
    -week
    -0.06
    暴
    -0.06
    Experiment
    -0.06
    POSITIVE LOGITS
     rámci
    0.07
    *****↵
    0.07
     Bowman
    0.06
     Pascal
    0.06
    WindowState
    0.06
    _blank
    0.06
    킨
    0.06
    adders
    0.06
     تلف
    0.06
     �
    0.06
    Act Density 0.018%

    No Known Activations