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

    Neuronpedia

    INDEX
    Explanations

    Getting Ready

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    +f
    -0.07
    處
    -0.07
    ft
    -0.07
    esimal
    -0.07
    Genesis
    -0.06
    彩票
    -0.06
     reconstruct
    -0.06
     Imam
    -0.06
     Mueller
    -0.06
    abble
    -0.06
    POSITIVE LOGITS
    olars
    0.06
    минист
    0.06
    十九
    0.06
    .swt
    0.06
    charts
    0.06
     lifestyles
    0.06
     boosting
    0.06
    .types
    0.06
    同志
    0.06
    -transitional
    0.06
    Act Density 0.033%

    No Known Activations