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

    Neuronpedia

    INDEX
    Explanations

    legal cases

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     SNAP
    -0.07
    SC
    -0.06
     am
    -0.06
    -G
    -0.06
    되고
    -0.06
    DataSet
    -0.06
    ":
    -0.06
    pora
    -0.06
    -A
    -0.06
     lö
    -0.06
    POSITIVE LOGITS
    .slice
    0.07
    ////////////////////////////////////////////////////////////////
    0.07
    ські
    0.06
    Carbon
    0.06
     Decomp
    0.06
    (mesh
    0.06
     Doom
    0.06
    озд
    0.06
    ={↵
    0.06
     нату
    0.06
    Act Density 0.031%

    No Known Activations