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

    Neuronpedia

    INDEX
    Explanations

    trough

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    LE
    0.55
    ITI
    0.55
    ーストラリア
    0.54
     Static
    0.53
    Its
    0.52
    ]$;
    0.52
    )$.
    0.51
     Utilization
    0.51
     Ignatius
    0.51
    Austin
    0.50
    POSITIVE LOGITS
    م
    0.75
     город
    0.68
     δύο
    0.64
     trough
    0.61
     یک
    0.59
     ασ
    0.59
     καθώς
    0.59
     protég
    0.57
    𝑛
    0.57
     społec
    0.56
    Act Density 0.000%

    No Known Activations