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

    Neuronpedia

    INDEX
    Explanations

    thus/therefore

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     papers
    -0.07
    ocht
    -0.07
    ifting
    -0.06
    _CURSOR
    -0.06
    dni
    -0.06
     đạt
    -0.06
    _-
    -0.06
    $/
    -0.06
    ımızda
    -0.06
    idia
    -0.06
    POSITIVE LOGITS
     therefore
    0.08
    	EIF
    0.07
    ，因此
    0.07
    .Deserialize
    0.07
    .datasource
    0.07
     sqlalchemy
    0.07
     hence
    0.07
    cannot
    0.07
    会
    0.06
     parent
    0.06
    Act Density 0.013%

    No Known Activations