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

    Neuronpedia

    INDEX
    Explanations

    canning

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     canning
    -1.16
     الحره
    -1.12
    OGND
    -1.02
    nologue
    -0.99
    WriteBarrier
    -0.91
    sidemargin
    -0.90
    XmlAccessType
    -0.88
    ⓧ
    -0.86
    TagMode
    -0.86
     ModelExpression
    -0.85
    POSITIVE LOGITS
    em
    0.45
     techo
    0.43
    son
    0.40
    StoredProcedure
    0.39
     son
    0.38
    ue
    0.38
    LA
    0.37
     pubb
    0.36
    d
    0.36
    ues
    0.35
    Act Density 0.289%

    No Known Activations