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

    Neuronpedia

    INDEX
    Explanations

    algorithmic differentiation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    h
    0.59
    ⃗
    0.58
     इमारत
    0.54
    主义
    0.53
    Compose
    0.51
     escalated
    0.51
     aim
    0.50
    istani
    0.50
    []>
    0.50
    TeV
    0.50
    POSITIVE LOGITS
    arity
    0.58
     fruition
    0.55
    onnay
    0.52
     Бы
    0.50
    ت
    0.50
    п
    0.50
    night
    0.49
     Đối
    0.48
     complemento
    0.47
    П
    0.47
    Act Density 0.027%

    No Known Activations