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

    Neuronpedia

    INDEX
    Explanations

    brightly colored, social security

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mischiev
    1.08
     rationally
    1.06
    (-\
    1.02
    "\
    1.02
    োত্তর
    1.01
    𝐝
    1.01
     상대
    0.98
     lineHeight
    0.98
    nity
    0.97
     Onun
    0.97
    POSITIVE LOGITS
    is
    1.23
    en
    1.19
    am
    1.17
    at
    1.14
     car
    1.08
    覀
    1.05
     sette
    1.02
    nov
    1.00
     ama
    1.00
     Cars
    0.99
    Act Density 0.000%

    No Known Activations