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

    Neuronpedia

    INDEX
    Explanations

    mass and quantitative data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     некоторым
    0.42
     formality
    0.40
    symmetric
    0.39
     sixteenth
    0.39
    |-
    0.39
     zumindest
    0.39
    otricha
    0.38
     vocabulary
    0.38
     suplement
    0.38
     некоторы
    0.38
    POSITIVE LOGITS
    堣
    0.53
     auprès
    0.50
     elég
    0.47
     what
    0.46
     projek
    0.45
     ceea
    0.44
    Վ
    0.44
     Kubernetes
    0.43
    បុ
    0.43
     sosyal
    0.43
    Act Density 0.001%

    No Known Activations