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

    Neuronpedia

    INDEX
    Explanations

    =

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    soon
    -0.07
     Turn
    -0.07
     flashing
    -0.07
     Vancouver
    -0.06
     partition
    -0.06
     fungi
    -0.06
     splitting
    -0.06
     Fans
    -0.06
     Enterprise
    -0.06
     se
    -0.06
    POSITIVE LOGITS
     lub
    0.07
     ці
    0.07
    eling
    0.07
    láš
    0.06
    -values
    0.06
    อท
    0.06
    �
    0.06
    _pts
    0.06
    ặt
    0.06
    駅徒歩
    0.06
    Act Density 0.013%

    No Known Activations