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

    Neuronpedia

    INDEX
    Explanations

    now

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Tb
    -0.06
    负责
    -0.06
     platí
    -0.06
     paci
    -0.06
    .cm
    -0.06
    _SY
    -0.06
     tặng
    -0.06
    -0.06
     zahl
    -0.06
    .cor
    -0.06
    POSITIVE LOGITS
     useDispatch
    0.08
    abase
    0.07
    ;j
    0.07
     al
    0.07
    _object
    0.07
     Warwick
    0.07
    _PRIVATE
    0.07
    shopping
    0.06
     xls
    0.06
     `;↵
    0.06
    Act Density 0.004%

    No Known Activations