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

    Neuronpedia

    INDEX
    Explanations

    Common English words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    рити
    -0.06
     fossils
    -0.06
    FormatException
    -0.06
    ریان
    -0.06
    htub
    -0.06
    coma
    -0.06
    Communication
    -0.06
     crate
    -0.06
     фай
    -0.06
    ระหว
    -0.06
    POSITIVE LOGITS
    494
    0.07
     プロ
    0.06
    Ⅵ
    0.06
     SENSOR
    0.06
     ):
    0.06
    CGSize
    0.06
     ').
    0.06
    .softmax
    0.06
     ');↵↵
    0.06
    ascimento
    0.06
    Act Density 0.036%

    No Known Activations