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

    Neuronpedia

    INDEX
    Explanations

    dark

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Brent
    -0.07
    -bo
    -0.06
    	mv
    -0.06
     boost
    -0.06
    .Connection
    -0.06
    ってきた
    -0.06
     bridges
    -0.06
    MouseListener
    -0.06
    。しかし
    -0.06
     Billy
    -0.06
    POSITIVE LOGITS
     dark
    0.09
     Dark
    0.09
    dark
    0.08
    icc
    0.08
    ask
    0.07
    οκ
    0.07
    `)
    0.07
     thổ
    0.07
    mark
    0.06
    dk
    0.06
    Act Density 0.014%

    No Known Activations