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

    Neuronpedia

    INDEX
    Explanations

    implify

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Category
    -0.07
    _sum
    -0.07
     по
    -0.07
     invoking
    -0.07
     excerpt
    -0.06
    4
    -0.06
    36
    -0.06
     category
    -0.06
    書
    -0.06
     landmark
    -0.06
    POSITIVE LOGITS
     mái
    0.07
    Karen
    0.07
    ????????????????
    0.07
     helicopt
    0.07
    _reservation
    0.07
     una
    0.06
     clases
    0.06
     distancia
    0.06
     Fortress
    0.06
    .ORDER
    0.06
    Act Density 0.024%

    No Known Activations