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

    Neuronpedia

    INDEX
    Explanations

    short-range distances

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     idols
    -0.08
    来た
    -0.07
    自有
    -0.07
     forfe
    -0.07
     groot
    -0.07
    projectId
    -0.07
    既
    -0.07
        		↵
    -0.07
     Crown
    -0.07
     tôn
    -0.07
    POSITIVE LOGITS
    LOYEE
    0.07
    #create
    0.07
     Widgets
    0.07
     estimating
    0.07
    热水器
    0.06
     Shaft
    0.06
    _auth
    0.06
    Enterprise
    0.06
     Dise
    0.06
    的危害
    0.06
    Act Density 0.011%

    No Known Activations