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

    Neuronpedia

    INDEX
    Explanations

    bracket

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     elle
    -0.07
     faç
    -0.07
     Slash
    -0.07
     Syn
    -0.07
    ຣ
    -0.07
     Img
    -0.07
     הגדול
    -0.07
     maç
    -0.06
    唢
    -0.06
     disks
    -0.06
    POSITIVE LOGITS
    conda
    0.08
    _workers
    0.07
    Unit
    0.07
    ????
    0.07
    违
    0.07
    bound
    0.07
    南路
    0.07
    _prof
    0.07
    胚胎
    0.07
    _contents
    0.07
    Act Density 0.032%

    No Known Activations