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

    Neuronpedia

    INDEX
    Explanations

    greatly

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _BU
    -0.07
     ukáz
    -0.06
     ob
    -0.06
     следующ
    -0.06
     RSA
    -0.06
    Index
    -0.06
    .bus
    -0.06
    sandbox
    -0.06
    .Last
    -0.06
     isIn
    -0.06
    POSITIVE LOGITS
    _spectrum
    0.07
    ocrat
    0.06
     sometime
    0.06
     conditioner
    0.06
     Throws
    0.06
     gé
    0.06
     هند
    0.06
    imate
    0.06
     exceedingly
    0.06
     america
    0.06
    Act Density 0.016%

    No Known Activations