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

    Neuronpedia

    INDEX
    Explanations

    activities they love

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    classList
    -0.07
    ีส
    -0.07
    п
    -0.06
     "<?
    -0.06
    ffiti
    -0.06
    ario
    -0.06
    _pot
    -0.06
     cos
    -0.06
    Controller
    -0.06
     �
    -0.06
    POSITIVE LOGITS
     Volunteer
    0.06
     unreal
    0.06
     reign
    0.06
     Visit
    0.06
    ocking
    0.06
     creators
    0.06
    rear
    0.06
    ош
    0.06
    """↵
    0.06
    inflate
    0.06
    Act Density 0.002%

    No Known Activations