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

    Neuronpedia

    INDEX
    Explanations

    was

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tra
    -0.06
     Sabbath
    -0.06
     brigade
    -0.06
     beautifully
    -0.06
    	Default
    -0.06
    	result
    -0.06
    :class
    -0.06
     організа
    -0.06
     ча
    -0.06
    uous
    -0.06
    POSITIVE LOGITS
    izzle
    0.07
    uffles
    0.07
    .switch
    0.07
    _SK
    0.06
    ρίας
    0.06
    Scr
    0.06
    classnames
    0.06
     escri
    0.06
     стоит
    0.06
    cls
    0.06
    Act Density 0.048%

    No Known Activations