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

    Neuronpedia

    INDEX
    Explanations

    this

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     egg
    -0.07
     Positions
    -0.07
     revenge
    -0.06
     Egg
    -0.06
    Using
    -0.06
    енное
    -0.06
     buttonWithType
    -0.06
     Using
    -0.06
     oper
    -0.06
     Triangle
    -0.06
    POSITIVE LOGITS
     dost
    0.07
    ¢
    0.07
    ailand
    0.06
    (clazz
    0.06
    (milliseconds
    0.06
     پش
    0.06
    iphers
    0.06
    misc
    0.06
     صور
    0.06
    KeyValuePair
    0.06
    Act Density 0.001%

    No Known Activations