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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ائج
    -0.06
    	range
    -0.06
     ท
    -0.06
     waiter
    -0.06
     laptop
    -0.06
     nodded
    -0.06
    .rb
    -0.06
     strang
    -0.06
     складу
    -0.06
     rol
    -0.06
    POSITIVE LOGITS
    애
    0.07
    avern
    0.07
    \Common
    0.06
     Moines
    0.06
    actus
    0.06
    іння
    0.06
    errar
    0.06
    .Blocks
    0.06
     چین
    0.06
     sensual
    0.06
    Act Density 0.005%

    No Known Activations