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

    Neuronpedia

    INDEX
    Explanations

    not

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     has
    -0.07
     endless
    -0.06
     have
    -0.06
    ски
    -0.06
     ';
↵
    -0.06
    肯
    -0.06
     Bru
    -0.06
    bove
    -0.06
     had
    -0.06
    ció
    -0.06
    POSITIVE LOGITS
    体系
    0.07
    Installed
    0.06
     \""
    0.06
    (context
    0.06
     nostalgic
    0.06
     Down
    0.06
          ↵↵
    0.06
    954
    0.06
     xung
    0.06
    .Perform
    0.06
    Act Density 0.011%

    No Known Activations