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

    Neuronpedia

    INDEX
    Explanations

    act

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    　ﾉ
    -0.07
     pháp
    -0.07
     nga
    -0.06
    branch
    -0.06
     aroma
    -0.06
    frm
    -0.06
     Favor
    -0.06
     ken
    -0.06
     diligently
    -0.06
     Rudd
    -0.06
    POSITIVE LOGITS
     تلك
    0.06
    Cases
    0.06
     الق
    0.06
    _ACC
    0.06
     findOne
    0.06
     naše
    0.06
    PC
    0.06
    듯
    0.06
    Slots
    0.06
    MODE
    0.06
    Act Density 0.003%

    No Known Activations