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

    Neuronpedia

    INDEX
    Explanations

    technical objects

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     McDonald
    -0.07
     dads
    -0.07
     Subscribe
    -0.07
    OUT
    -0.06
     شد
    -0.06
    ект
    -0.06
     Widow
    -0.06
    laşma
    -0.06
    Ư
    -0.06
     JPG
    -0.06
    POSITIVE LOGITS
     βα
    0.06
     صاد
    0.06
    crime
    0.06
    chemical
    0.06
    ,var
    0.06
    ...,
    0.06
     aldığı
    0.06
     bringing
    0.06
     роль
    0.06
     lidi
    0.06
    Act Density 0.170%

    No Known Activations