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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and Greek letters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     rebell
    0.72
     revenge
    0.72
     dishon
    0.69
     venge
    0.68
     vengeance
    0.66
     redemption
    0.64
     prophes
    0.64
     prophecies
    0.64
     murders
    0.63
     Nuevo
    0.63
    POSITIVE LOGITS
    goài
    0.76
    {\
    0.75
    Weyl
    0.74
    mathcal
    0.72
    >\<^
    0.68
    mathscr
    0.67
    icked
    0.65
    Dirac
    0.64
    مراجع
    0.63
    ння
    0.62
    Act Density 0.008%

    No Known Activations