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

    Neuronpedia

    INDEX
    Explanations

    articles in multiple languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <unused626>
    0.15
     spermatozoa
    0.15
     nitrog
    0.14
     pept
    0.14
     enzym
    0.13
     calcareous
    0.13
    澼
    0.13
     tubercul
    0.13
    Benzyloxy
    0.13
    猞
    0.13
    POSITIVE LOGITS
    -
    0.23
    +
    0.19
    /
    0.18
    0
    0.18
    5
    0.16
    *
    0.16
    ↵
    0.15
    .
    0.15
    6
    0.15
    ?
    0.15
    Act Density 0.025%

    No Known Activations