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

    Neuronpedia

    INDEX
    Explanations

    life and individuals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    7
    2.36
    rinsic
    2.27
    6
    2.23
    8
    2.15
    9
    2.02
    3
    1.99
     makeSound
    1.93
    5
    1.92
    4
    1.91
    }°
    1.90
    POSITIVE LOGITS
     historians
    2.83
     reckons
    2.38
    astic
    2.25
     Ramb
    2.24
    dated
    2.23
     lược
    2.22
     leaks
    2.22
    囝
    2.20
     historian
    2.19
     selectors
    2.18
    Act Density 0.000%

    No Known Activations