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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    lambda
    -0.07
     pleasures
    -0.06
    -price
    -0.06
    ]])
    -0.06
     Wesley
    -0.06
     Petit
    -0.06
    Theta
    -0.06
     metals
    -0.06
    -going
    -0.06
    оны
    -0.06
    POSITIVE LOGITS
    ่างๆ
    0.07
    をお
    0.07
     aras
    0.06
    _HAS
    0.06
    HeaderText
    0.06
    odia
    0.06
     누
    0.06
    áj
    0.06
     Comedy
    0.06
    ImageRelation
    0.06
    Act Density 0.002%

    No Known Activations