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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _started
    -0.06
    _attach
    -0.06
    =h
    -0.06
     rev
    -0.06
    variables
    -0.06
     caric
    -0.06
     Chern
    -0.06
    KERNEL
    -0.05
     Hop
    -0.05
     h
    -0.05
    POSITIVE LOGITS
    benhavn
    0.07
    บาท
    0.07
    -logo
    0.07
     China
    0.07
     exploring
    0.07
    PLOY
    0.06
    县
    0.06
    TreeNode
    0.06
     กรก
    0.06
    albums
    0.06
    Act Density 0.002%

    No Known Activations