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

    Neuronpedia

    INDEX
    Explanations

    we

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lifestyle
    -0.08
     gerne
    -0.08
     toppings
    -0.08
     greetings
    -0.08
     Lifestyle
    -0.07
    横
    -0.07
     enthusiasts
    -0.07
    يغ
    -0.07
     അവതരിപ്പ
    -0.07
     친
    -0.07
    POSITIVE LOGITS
    Clas
    0.10
     ಸಂಭವ
    0.09
    Tall
    0.08
    Pending
    0.08
     decidir
    0.08
    icious
    0.08
     contemplating
    0.08
    Asign
    0.07
     Midlands
    0.07
     deciding
    0.07
    Act Density 0.038%

    No Known Activations