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

    Neuronpedia

    INDEX
    Explanations

    random strings and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ➣
    0.69
    🛂
    0.68
    🕣
    0.68
     procrastination
    0.67
     extrapol
    0.67
     hydrology
    0.66
     immersive
    0.65
     frosting
    0.64
    🙍
    0.64
    鸨
    0.62
    POSITIVE LOGITS
    L
    0.90
    T
    0.85
    q
    0.77
    b
    0.77
    A
    0.75
    f
    0.74
    r
    0.73
    R
    0.72
    O
    0.71
    E
    0.70
    Act Density 0.022%

    No Known Activations