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

    Neuronpedia

    INDEX
    Explanations

    accessing properties like body.plan

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    thisTrack
    0.31
    粝
    0.28
    秕
    0.28
    𒊬
    0.27
    ガラス
    0.26
    𒇽
    0.26
    UILLER
    0.26
    海水
    0.26
     витами
    0.26
     анато
    0.25
    POSITIVE LOGITS
    get
    0.38
     get
    0.34
     the
    0.33
     f
    0.31
     G
    0.30
    value
    0.29
    id
    0.29
     own
    0.28
    d
    0.28
    w
    0.28
    Act Density 0.124%

    No Known Activations