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

    Neuronpedia

    INDEX
    Explanations

    path or purpose

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ......
    0.49
     ......
    0.43
    ..........
    0.40
     zub
    0.38
    angana
    0.38
    .....
    0.37
    azor
    0.37
     .......
    0.36
    ]，
    0.36
    .......
    0.36
    POSITIVE LOGITS
     Path
    0.41
    Path
    0.40
     Tanger
    0.39
     کیف
    0.39
     तर
    0.38
    Purpose
    0.38
     Whenever
    0.37
     Go
    0.37
    path
    0.37
     path
    0.37
    Act Density 0.000%

    No Known Activations