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

    Neuronpedia

    INDEX
    Explanations

    tickets for sale

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     करिकुलम
    0.47
     kể
    0.46
    Celeron
    0.43
    ⚉
    0.42
    쉼
    0.42
     стру
    0.41
     рит
    0.41
     Accounts
    0.40
     đáp
    0.40
    klı
    0.40
    POSITIVE LOGITS
     amist
    0.44
    1
    0.43
    relations
    0.42
    debounce
    0.41
     l
    0.41
    online
    0.40
     pollo
    0.39
     revista
    0.39
    agu
    0.38
    violations
    0.38
    Act Density 0.002%

    No Known Activations