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

    Neuronpedia

    INDEX
    Explanations

    Western

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mongo
    -0.07
    Blockly
    -0.06
    猜
    -0.06
    abilmek
    -0.06
    čů
    -0.06
     Pok
    -0.06
    .sock
    -0.06
     Zend
    -0.06
     Kv
    -0.06
    分钟
    -0.06
    POSITIVE LOGITS
     vibrating
    0.07
     reorder
    0.07
     acting
    0.06
     sci
    0.06
     defense
    0.06
     MP
    0.06
     decreasing
    0.06
    uring
    0.06
     whales
    0.06
    photo
    0.06
    Act Density 0.001%

    No Known Activations