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

    Neuronpedia

    INDEX
    Explanations

    until

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     encour
    -0.07
    就够
    -0.07
     Betting
    -0.06
    會員規
    -0.06
    poses
    -0.06
     מכל
    -0.06
     vec
    -0.06
    Leaks
    -0.06
    アジア
    -0.06
    副
    -0.06
    POSITIVE LOGITS
    .EventHandler
    0.07
     ____
    0.07
    	update
    0.07
    0.06
    '''
    0.06
    ____
    0.06
    _runtime
    0.06
    专卖店
    0.06
     request
    0.06
     ранее
    0.06
    Act Density 0.008%

    No Known Activations