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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ward
    -0.06
     Presidential
    -0.06
    Gets
    -0.06
    .place
    -0.06
    _SUB
    -0.06
     alloy
    -0.06
    verting
    -0.06
     became
    -0.06
    Protected
    -0.06
    ornment
    -0.06
    POSITIVE LOGITS
    แนว
    0.07
     fazer
    0.07
     продаж
    0.07
    洗
    0.07
    043
    0.07
    나요
    0.07
     建
    0.07
     متخصص
    0.06
     meslek
    0.06
    。\
    0.06
    Act Density 0.000%

    No Known Activations