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

    Neuronpedia

    INDEX
    Explanations

    Programming context

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Merit
    -0.07
    NonQuery
    -0.07
     doivent
    -0.07
     esteem
    -0.07
     chk
    -0.07
     emot
    -0.07
     themed
    -0.07
     Amir
    -0.07
     Sw
    -0.07
    Odd
    -0.07
    POSITIVE LOGITS
    稿件
    0.07
    ご利用
    0.07
    暴
    0.07
    _TICK
    0.07
    ➜
    0.07
     trouble
    0.06
    (project
    0.06
    /access
    0.06
    huge
    0.06
    _discount
    0.06
    Act Density 0.049%

    No Known Activations