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

    Neuronpedia

    INDEX
    Explanations

    forms of "to be"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .StringUtils
    -0.06
     silenced
    -0.06
    	super
    -0.06
    opol
    -0.06
    Hop
    -0.06
    tracked
    -0.06
    ��
    -0.06
    Stra
    -0.06
     �
    -0.06
    spam
    -0.06
    POSITIVE LOGITS
     закон
    0.07
    -plugins
    0.07
     дост
    0.07
     etiqu
    0.07
     festival
    0.07
     loft
    0.07
    estival
    0.06
     grande
    0.06
     tôn
    0.06
     dejar
    0.06
    Act Density 0.048%

    No Known Activations