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

    Neuronpedia

    INDEX
    Explanations

    sequence characters and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    icolo
    1.13
     छोड़
    1.13
    Џ
    1.12
     prism
    1.05
     manometer
    1.00
    ছনে
    0.96
    itis
    0.96
     pharetra
    0.96
    ೋ
    0.95
    程式
    0.95
    POSITIVE LOGITS
     volna
    1.14
    z
    1.13
    ف
    1.02
    մ
    1.01
    soaked
    1.01
     бы
    1.01
     কথিত
    1.00
    MRS
    0.99
    ا
    0.99
    饌
    0.98
    Act Density 0.000%

    No Known Activations