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

    Neuronpedia

    INDEX
    Explanations

    Git

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     salt
    -0.08
     الاستخدام
    -0.08
     clarification
    -0.08
     aliviar
    -0.07
     tiếp
    -0.07
    ිරි
    -0.07
     libc
    -0.07
    ාල
    -0.07
     nausea
    -0.07
    شرح
    -0.07
    POSITIVE LOGITS
    浩
    0.07
    ，当
    0.07
     convent
    0.07
     Zem
    0.07
     feeders
    0.07
    CV
    0.07
     Accelerator
    0.07
     umfang
    0.07
     поступ
    0.07
     Popup
    0.07
    Act Density 0.006%

    No Known Activations