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

    Neuronpedia

    INDEX
    Explanations

    Illuminate Eloquent ORM concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    aaaa
    0.41
    rmi
    0.39
     bachelor
    0.38
    cz
    0.38
    삼
    0.38
     ra
    0.37
    aaaaaaaa
    0.37
     =
    0.37
    ocup
    0.37
    про
    0.37
    POSITIVE LOGITS
    Contracts
    0.54
     Contracts
    0.52
    Fluent
    0.50
    Mayo
    0.47
    contracts
    0.46
     Fluent
    0.45
    Contract
    0.43
     Supportive
    0.43
    fluent
    0.43
    ీల
    0.42
    Act Density 0.002%

    No Known Activations