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

    Neuronpedia

    INDEX
    Explanations

    def

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gameOver
    -0.07
    bh
    -0.06
    _matrices
    -0.06
    иш
    -0.06
     compens
    -0.06
     puedes
    -0.06
    英雄
    -0.06
    cw
    -0.06
     wan
    -0.06
    Guard
    -0.06
    POSITIVE LOGITS
     EDIT
    0.07
     рублей
    0.07
    agraph
    0.06
    ัจจ
    0.06
     picture
    0.06
     BITS
    0.06
     dolay
    0.06
     Thoughts
    0.06
     Crypto
    0.06
    .purchase
    0.06
    Act Density 0.005%

    No Known Activations