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

    Neuronpedia

    INDEX
    Explanations

    connectors and conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    According
    1.27
    However
    1.26
    What
    1.19
    When
    1.18
    How
    1.15
    While
    1.15
    Furthermore
    1.14
    Why
    1.13
    <h3>
    1.12
    “
    1.12
    POSITIVE LOGITS
     និង
    0.82
    및
    0.80
    <unused289>
    0.78
    និង
    0.75
    PatientR
    0.73
    <unused326>
    0.70
    <unused550>
    0.70
    <unused1877>
    0.69
    <unused263>
    0.68
     sila
    0.67
    Act Density 0.001%

    No Known Activations