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

    Neuronpedia

    INDEX
    Explanations

    selector and desired state

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    shiny
    0.40
    ಟಕ
    0.39
     tbody
    0.39
    টাল
    0.39
    alya
    0.39
    ोब
    0.39
    ន្ធ
    0.38
    ខ្សែ
    0.38
    tob
    0.38
     tokenizer
    0.38
    POSITIVE LOGITS
    Alternate
    0.42
    呮
    0.42
    receptor
    0.40
    ProfileAction
    0.39
    乨
    0.38
    Defense
    0.38
    Selector
    0.38
     resultContent
    0.38
    忆
    0.38
    宻
    0.38
    Act Density 0.000%

    No Known Activations