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

    Neuronpedia

    INDEX
    Explanations

    only

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     weeds
    -0.07
     (()
    -0.06
     fluent
    -0.06
    >List
    -0.06
     chiếu
    -0.06
     Examples
    -0.06
     mimic
    -0.06
     fileList
    -0.06
     dose
    -0.06
    dismiss
    -0.06
    POSITIVE LOGITS
    *width
    0.06
    .random
    0.06
     denen
    0.06
     <",
    0.06
    寶
    0.06
    □
    0.06
     �
    0.06
     astrology
    0.06
    <uint
    0.06
     York
    0.06
    Act Density 0.005%

    No Known Activations