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

    Neuronpedia

    INDEX
    Explanations

    'a' followed by specific words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    กัน
    0.41
    Structured
    0.38
    竑
    0.38
    veless
    0.37
    Ⲓ
    0.37
    釣り
    0.36
    Aws
    0.36
    ർത്ത
    0.36
    VERSE
    0.36
    Celtic
    0.35
    POSITIVE LOGITS
    }?
    0.41
    >?
    0.40
    atma
    0.40
     nói
    0.39
    at
    0.38
    form
    0.38
    b
    0.38
    ‘
    0.38
    .?
    0.37
    ాన్
    0.37
    Act Density 0.001%

    No Known Activations