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

    Neuronpedia

    INDEX
    Explanations

    0

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    륜
    -0.07
    _recommend
    -0.07
    Voltage
    -0.07
     officers
    -0.06
    奶油
    -0.06
    Container
    -0.06
    VO
    -0.06
    阀门
    -0.06
    _registro
    -0.06
    _code
    -0.06
    POSITIVE LOGITS
     semble
    0.08
    ää
    0.07
     roofs
    0.07
    ologne
    0.07
     wxT
    0.07
    🦅
    0.07
    😸
    0.07
     means
    0.07
    قضايا
    0.07
    ẳ
    0.07
    Act Density 0.013%

    No Known Activations