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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     boyfriend
    -0.07
    χία
    -0.07
    ियन
    -0.07
    173
    -0.06
     Tennis
    -0.06
     Crud
    -0.06
     cocoa
    -0.06
    .camera
    -0.06
    _closure
    -0.06
     Cone
    -0.06
    POSITIVE LOGITS
    废
    0.07
    达
    0.06
    endency
    0.06
    uggest
    0.06
    xlabel
    0.06
    _DLL
    0.06
     Lun
    0.06
     지나
    0.06
     ain
    0.06
    ages
    0.06
    Act Density 0.119%

    No Known Activations