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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     variable
    -0.08
    checking
    -0.07
     poets
    -0.07
    ={
    -0.07
    -0.07
    港
    -0.07
    {\
    -0.07
    _login
    -0.07
                                                    ↵
    -0.07
    _GREEN
    -0.07
    POSITIVE LOGITS
    habit
    0.07
    łoży
    0.07
     housed
    0.07
    尾巴
    0.07
    eka
    0.07
    착
    0.07
    没法
    0.06
    izona
    0.06
     Valve
    0.06
     ashes
    0.06
    Act Density 0.020%

    No Known Activations