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

    Neuronpedia

    INDEX
    Explanations

    B and CR followed by numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    endtime
    -0.07
     August
    -0.07
     //[
    -0.07
    гот
    -0.07
    房间
    -0.07
     fotbal
    -0.07
    agal
    -0.07
     getNode
    -0.06
     Cop
    -0.06
     sharper
    -0.06
    POSITIVE LOGITS
     Chap
    0.06
     Dut
    0.06
     dua
    0.06
    rians
    0.06
    に入
    0.06
     Mild
    0.06
    ’nın
    0.06
     tit
    0.06
    ussions
    0.06
    .case
    0.06
    Act Density 0.029%

    No Known Activations