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

    Neuronpedia

    INDEX
    Explanations

    To

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Does
    0.74
     does
    0.72
     Does
    0.70
    ring
    0.66
    Ring
    0.66
    does
    0.65
     representation
    0.65
     continues
    0.64
    リング
    0.63
    Hope
    0.61
    POSITIVE LOGITS
    To
    0.85
    TO
    0.82
     To
    0.82
     перед
    0.81
     Quando
    0.75
    Перед
    0.75
     før
    0.74
     bevor
    0.73
    屻
    0.73
     тө
    0.73
    Act Density 0.030%

    No Known Activations