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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     facil
    -0.08
     že
    -0.07
    IDI
    -0.07
    Gift
    -0.06
     shm
    -0.06
    exc
    -0.06
    (EXPR
    -0.06
     hình
    -0.06
    TYPO
    -0.06
    either
    -0.06
    POSITIVE LOGITS
    8
    0.07
    12
    0.07
     GP
    0.07
    4
    0.07
    17
    0.07
    5
    0.07
    539
    0.07
    2
    0.07
    23
    0.06
    .accounts
    0.06
    Act Density 0.030%

    No Known Activations