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

    Neuronpedia

    INDEX
    Explanations

    React component definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dijadikan
    0.39
    ިން
    0.39
     کوشش
    0.38
    ]]).
    0.37
    dió
    0.37
     créé
    0.37
    coli
    0.36
    aff
    0.35
    ]|[
    0.35
     operazioni
    0.35
    POSITIVE LOGITS
    ({
    0.75
     ({
    0.64
    ({})
    0.52
    props
    0.45
    内容的
    0.44
    ({'
    0.41
    ({...
    0.41
     pure
    0.41
     component
    0.40
     Content
    0.40
    Act Density 0.002%

    No Known Activations