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

    Neuronpedia

    INDEX
    Explanations

    reporting future events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     reimag
    0.40
     rebuke
    0.38
     (“
    0.36
     voilà
    0.34
     inspires
    0.34
     resonate
    0.34
     argu
    0.33
    ！
    0.33
     defies
    0.33
    ête
    0.33
    POSITIVE LOGITS
    据悉
    0.47
     الخدمات
    0.39
    한편
    0.38
     خواهد
    0.37
     Plans
    0.37
     PLANS
    0.37
     Presently
    0.37
     Services
    0.35
    其他的
    0.35
     STORE
    0.35
    Act Density 0.001%

    No Known Activations