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

    Neuronpedia

    INDEX
    Explanations

    Eyeshadow and French

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    portal
    -0.07
     форме
    -0.07
    Κα
    -0.06
     ____
    -0.06
     rosa
    -0.06
     Curriculum
    -0.06
     عصر
    -0.06
     آنان
    -0.06
     Behaviour
    -0.06
    _INS
    -0.06
    POSITIVE LOGITS
    adow
    0.12
     Corvette
    0.11
    'y
    0.10
    iper
    0.09
    ’y
    0.09
    ий
    0.07
     viper
    0.07
     Voy
    0.06
    attro
    0.06
     الجديد
    0.06
    Act Density 0.001%

    No Known Activations