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

    Neuronpedia

    INDEX
    Explanations

    vector space

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mỹ
    -0.07
    -gr
    -0.07
     Crit
    -0.07
     rod
    -0.06
    GAME
    -0.06
     fingert
    -0.06
    OTA
    -0.06
    喙
    -0.06
    مصر
    -0.06
    สด
    -0.06
    POSITIVE LOGITS
     bone
    0.07
    ﲢ
    0.07
    ually
    0.07
    .response
    0.06
    /npm
    0.06
     المتعل
    0.06
    ทะ
    0.06
    的一
    0.06
    ー�
    0.06
    zeich
    0.06
    Act Density 0.017%

    No Known Activations