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

    Neuronpedia

    INDEX
    Explanations

    UI buttons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Crom
    -0.07
     Ost
    -0.06
    dbuf
    -0.06
    иф
    -0.06
     Elaine
    -0.06
     яв
    -0.05
     Cath
    -0.05
    +W
    -0.05
     privileges
    -0.05
    priv
    -0.05
    POSITIVE LOGITS
     Kasich
    0.07
     banka
    0.07
    _quote
    0.07
    ckett
    0.07
    cess
    0.06
    ringe
    0.06
     ül
    0.06
    Courier
    0.06
    バス
    0.06
    년
    0.06
    Act Density 0.034%

    No Known Activations