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

    Neuronpedia

    INDEX
    Explanations

    Combustion engines/exhaust systems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     model
    -0.07
     flying
    -0.07
    ált
    -0.07
    하다
    -0.06
    CAF
    -0.06
    uder
    -0.06
    굴
    -0.06
     underestimate
    -0.06
     recycling
    -0.06
    olt
    -0.06
    POSITIVE LOGITS
    eview
    0.07
    *n
    0.06
    ＞
    0.06
    _attrib
    0.06
    oreach
    0.06
    […]
    0.06
    pción
    0.06
    ,...
    0.06
    compiler
    0.06
    ↵  ↵
    0.06
    Act Density 0.024%

    No Known Activations