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

    Neuronpedia

    INDEX
    Explanations

    ethics approval number

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Adoption
    -0.08
    能耗
    -0.07
     Automotive
    -0.07
    _nullable
    -0.07
    loops
    -0.07
     individ
    -0.07
    oka
    -0.06
     Decode
    -0.06
     efficiencies
    -0.06
     hade
    -0.06
    POSITIVE LOGITS
     beğen
    0.07
    "],"
    0.07
     опас
    0.06
    _ch
    0.06
    怎样
    0.06
    他还
    0.06
    还要
    0.06
     garant
    0.06
    堪
    0.06
    etermin
    0.06
    Act Density 0.012%

    No Known Activations