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

    Neuronpedia

    INDEX
    Explanations

    tuning

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    赍
    -0.07
     bureaucrats
    -0.07
     BM
    -0.07
     dgv
    -0.07
    .executor
    -0.07
     expectancy
    -0.07
    ]|
    -0.07
    .increment
    -0.07
    .EMPTY
    -0.07
    伴随
    -0.06
    POSITIVE LOGITS
    anners
    0.08
    celona
    0.07
    rell
    0.07
    ented
    0.07
    structuring
    0.07
    style
    0.07
    �
    0.06
    łem
    0.06
    qt
    0.06
    liner
    0.06
    Act Density 0.003%

    No Known Activations