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

    Neuronpedia

    INDEX
    Explanations

    dried

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _refs
    -0.07
     TBranch
    -0.07
     washed
    -0.07
    哭
    -0.06
     ذات
    -0.06
    .stopPropagation
    -0.06
    �
    -0.06
     wont
    -0.06
    -Cds
    -0.06
     přísluš
    -0.06
    POSITIVE LOGITS
    Menus
    0.07
    řet
    0.06
     advisor
    0.06
     ------>
    0.06
     adjustments
    0.06
    .imp
    0.06
    έντ
    0.06
    ảo
    0.06
     invo
    0.06
     penalty
    0.06
    Act Density 0.000%

    No Known Activations