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

    Neuronpedia

    INDEX
    Explanations

    unwanted calls

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     eigen
    -0.07
    บรรยาก
    -0.07
    障碍
    -0.07
    �
    -0.06
     Consulting
    -0.06
    ጨ
    -0.06
    熄
    -0.06
     zost
    -0.06
    瞻
    -0.06
     overhead
    -0.06
    POSITIVE LOGITS
     DataFrame
    0.10
    슛
    0.07
    Genres
    0.07
    .g
    0.07
    .Dictionary
    0.07
    trys
    0.07
    .Use
    0.07
    getTable
    0.07
     notions
    0.07
    .readString
    0.07
    Act Density 0.032%

    No Known Activations