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

    Neuronpedia

    INDEX
    Explanations

    alone, itself

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     itself
    -1.80
    itself
    -1.36
     alone
    -1.11
     Itself
    -1.10
     overall
    -0.95
     himself
    -0.91
     themselves
    -0.89
     herself
    -0.88
    本身
    -0.82
     نفسها
    -0.78
    POSITIVE LOGITS
    tagHelperRunner
    1.27
     Normdatei
    0.97
    AndEndTag
    0.88
    ConstraintMaker
    0.84
    setVerticalGroup
    0.81
    posedge
    0.81
    Autoritní
    0.79
    DoubleQuotes
    0.79
    存于互联网档案馆
    0.77
    ValueStyle
    0.77
    Act Density 0.205%

    No Known Activations