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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     изготов
    -0.08
     اهمیت
    -0.07
    aurus
    -0.06
    іст
    -0.06
     timing
    -0.06
    �
    -0.06
     таблиц
    -0.06
    吨
    -0.06
    Marca
    -0.06
     Най
    -0.06
    POSITIVE LOGITS
    งก
    0.07
    -show
    0.07
    parcel
    0.07
     dem
    0.06
    ################################################################################↵
    0.06
     mystery
    0.06
    ticket
    0.06
    relude
    0.06
    /ubuntu
    0.06
     scrollTop
    0.06
    Act Density 0.000%

    No Known Activations