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

    Neuronpedia

    INDEX
    Explanations

    system management

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sauna
    -0.07
     drink
    -0.07
     ense
    -0.07
    correo
    -0.06
    사무
    -0.06
    .setOn
    -0.06
    	RT
    -0.06
     푸
    -0.06
     돌아
    -0.06
     rubbing
    -0.06
    POSITIVE LOGITS
     redistributed
    0.06
    列表
    0.06
    NASDAQ
    0.05
    params
    0.05
    --------------------------------------------------------------------------------
    0.05
     carbohydr
    0.05
    ışı
    0.05
     "#{
    0.05
     conclus
    0.05
     dys
    0.05
    Act Density 0.048%

    No Known Activations