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

    Neuronpedia

    INDEX
    Explanations

    .T

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Huffman
    -0.07
     vanish
    -0.07
    [][
    -0.07
    "])
↵
    -0.07
    ////////////////////////////////////////////////////////////////////////
    -0.06
    skirts
    -0.06
    .DESC
    -0.06
     catalogue
    -0.06
    soup
    -0.06
    ymbol
    -0.06
    POSITIVE LOGITS
    墓
    0.07
    ứ
    0.07
     �
    0.06
     основ
    0.06
     Controllers
    0.06
     인간
    0.06
    .jsx
    0.06
    urse
    0.06
     Grey
    0.06
     expressive
    0.06
    Act Density 0.001%

    No Known Activations