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

    Neuronpedia

    INDEX
    Explanations

    lieu

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    fy
    -0.07
    Rows
    -0.07
    ###↵
    -0.07
    ]")↵
    -0.06
     DF
    -0.06
     TD
    -0.06
     Дж
    -0.06
    .square
    -0.06
     powder
    -0.06
    ------+
    -0.06
    POSITIVE LOGITS
    воля
    0.08
    trfs
    0.07
    letics
    0.07
    Submitting
    0.07
    _REGISTER
    0.07
    AGE
    0.07
    .or
    0.06
    ้ค
    0.06
    _reordered
    0.06
    alon
    0.06
    Act Density 0.004%

    No Known Activations