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

    Neuronpedia

    INDEX
    Explanations

    URLs/DOIs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     двух
    -0.07
     боку
    -0.07
     Lego
    -0.06
     صند
    -0.06
    ेल
    -0.06
     VERSION
    -0.06
     ль
    -0.06
    �
    -0.06
    �
    -0.06
    ед
    -0.06
    POSITIVE LOGITS
    loadModel
    0.07
     التاريخ
    0.07
    	name
    0.07
     Controllers
    0.06
     мис
    0.06
     Estr
    0.06
    Ệ
    0.06
     violently
    0.06
     Achilles
    0.06
    .matches
    0.06
    Act Density 0.000%

    No Known Activations