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

    Neuronpedia

    INDEX
    Explanations

    programming and months

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    0.95
    에
    0.88
    ים
    0.86
     collaboratively
    0.84
    dport
    0.83
    ಕ್ಕೆ
    0.78
    ਆਂ
    0.76
    circledR
    0.74
    ம்
    0.74
    ाने
    0.74
    POSITIVE LOGITS
     HA
    0.95
    Obl
    0.92
    ina
    0.92
     amino
    0.90
    Zara
    0.88
    ino
    0.87
    ier
    0.86
    IER
    0.85
     LE
    0.85
     Amino
    0.85
    Act Density 0.000%

    No Known Activations