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

    Neuronpedia

    INDEX
    Explanations

    mantle

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    85
    -0.07
    56
    -0.07
     Ireland
    -0.07
    >>>>
    -0.07
    dur
    -0.07
    -0.06
     blue
    -0.06
    武器
    -0.06
     decisions
    -0.06
    794
    -0.06
    POSITIVE LOGITS
     mantle
    0.15
     mant
    0.13
     Mant
    0.12
    mant
    0.08
    ant
    0.08
    [cnt
    0.07
     parentNode
    0.07
    ignet
    0.07
     sts
    0.07
     thrust
    0.07
    Act Density 0.003%

    No Known Activations