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

    Neuronpedia

    INDEX
    Explanations

    setting priorities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Osc
    0.43
    illusion
    0.43
    newMessage
    0.41
    new
    0.40
     Những
    0.39
    notifications
    0.37
    GEM
    0.37
    nullable
    0.37
    mature
    0.37
     Atual
    0.36
    POSITIVE LOGITS
     priority
    0.97
     priorities
    0.96
     prioritise
    0.93
     приорите
    0.92
     priorit
    0.92
     prioritizing
    0.90
     prioritized
    0.88
     prioritization
    0.88
    優先
    0.88
     prioritize
    0.86
    Act Density 0.184%

    No Known Activations