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

    Neuronpedia

    INDEX
    Explanations

    code examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    arc
    0.74
    rich
    0.74
     Title
    0.69
    title
    0.69
    อิ
    0.67
    str
    0.67
     Charles
    0.66
    ‎
    0.66
    only
    0.66
    Charles
    0.65
    POSITIVE LOGITS
     crypto
    1.02
     scouts
    1.00
    花
    1.00
     scout
    1.00
     goalkeeper
    1.00
    ᕆ
    0.99
    TRE
    0.98
     வால்பேப்பர்கள்
    0.98
    isAssignableFrom
    0.97
    ﻂ
    0.97
    Act Density 0.018%

    No Known Activations