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

    Neuronpedia

    INDEX
    Explanations

    periods

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     below
    0.76
     Below
    0.76
    below
    0.69
    Below
    0.68
     ниже
    0.63
     above
    0.54
    以下
    0.53
    above
    0.53
     abaixo
    0.53
     BELOW
    0.53
    POSITIVE LOGITS
     Unterstützung
    0.49
    Support
    0.48
     support
    0.48
     ser
    0.47
     supporto
    0.45
     apoyo
    0.44
     підтрим
    0.43
     Support
    0.43
     soporte
    0.43
     action
    0.40
    Act Density 0.004%

    No Known Activations