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

    Neuronpedia

    INDEX
    Explanations

    alphanumeric characters separated by symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ه
    1.27
    ش
    1.27
    ☓
    1.02
    𝘆
    0.91
     R
    0.90
    レ
    0.90
    न
    0.89
    ನಲ್ಲಿ
    0.89
    रे
    0.88
    𝙜
    0.88
    POSITIVE LOGITS
     которые
    1.13
     যাইহোক
    1.13
    SPs
    1.13
    ികിത്സ
    1.12
    izes
    1.11
    hankelijk
    1.07
    7
    1.07
    gangen
    1.06
    皞
    1.05
    ize
    1.05
    Act Density 0.470%

    No Known Activations