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

    Neuronpedia

    INDEX
    Explanations

    numbers and punctuation after hexadecimal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    reflectionMap
    0.46
     libsql
    0.45
    ﮅ
    0.44
    跏
    0.43
     BGPS
    0.43
    ꞎ
    0.42
    jobNumber
    0.42
     dersimizde
    0.42
    ೇವಿನ
    0.42
    اونلو
    0.41
    POSITIVE LOGITS
    less
    0.42
    .
    0.41
    ।
    0.41
     (
    0.40
    h
    0.39
    Short
    0.38
    ↵
    0.38
    O
    0.38
    Don
    0.37
    After
    0.37
    Act Density 0.016%

    No Known Activations