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

    Neuronpedia

    INDEX
    Explanations

    time horizon

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    本次
    0.82
    一時
    0.78
    డం
    0.74
    這次
    0.73
    зя
    0.69
     danas
    0.69
     derzeit
    0.68
    AREA
    0.68
    Hydrochloride
    0.67
    owę
    0.67
    POSITIVE LOGITS
     ago
    1.87
     spent
    1.79
     elapse
    1.76
     elapsed
    1.64
     동안
    1.44
    spent
    1.33
     boyunca
    1.29
     Spent
    1.26
    동안
    1.26
    Elapsed
    1.22
    Act Density 0.417%

    No Known Activations