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

    Neuronpedia

    INDEX
    Explanations

    querying data or responses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    elevationMap
    0.48
    鈳
    0.46
     Mares
    0.45
    矨
    0.43
    サロン
    0.40
    鸹
    0.40
    Mapping
    0.40
    雩
    0.39
    𝄞
    0.39
    ี่ยม
    0.38
    POSITIVE LOGITS
    get
    0.52
     get
    0.51
     first
    0.50
     all
    0.50
     filter
    0.50
     order
    0.48
     texts
    0.47
     text
    0.46
    text
    0.45
    order
    0.43
    Act Density 0.015%

    No Known Activations