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

    Neuronpedia

    INDEX
    Explanations

    dis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -/
    -0.07
    _udp
    -0.07
    fraction
    -0.07
     tic
    -0.07
    ].
    -0.06
    atoi
    -0.06
    (PARAM
    -0.06
     نخ
    -0.06
     дер
    -0.06
    "]');↵
    -0.06
    POSITIVE LOGITS
    elligent
    0.07
    [list
    0.06
    ram
    0.06
    ceso
    0.06
    .spotify
    0.06
    イヤ
    0.06
     efficient
    0.06
    ائرة
    0.06
    execute
    0.06
     condo
    0.06
    Act Density 0.001%

    No Known Activations