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

    Neuronpedia

    INDEX
    Explanations

    regular expression

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     conseg
    0.91
     escre
    0.86
    getWorld
    0.84
    γκε
    0.83
    >:</
    0.82
    ೋತಿ
    0.81
    OT
    0.81
    SDL
    0.81
     Miscellaneous
    0.80
     حاجه
    0.80
    POSITIVE LOGITS
     colonies
    0.89
    示した
    0.86
    ร์
    0.85
     Roundup
    0.84
    ​]]
    0.84
    ๑
    0.84
     mắt
    0.84
     vera
    0.83
    示す
    0.80
     carpets
    0.80
    Act Density 0.171%

    No Known Activations