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

    Neuronpedia

    INDEX
    Explanations

    explain

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ask
    -0.07
    Ey
    -0.06
    rozen
    -0.06
     mash
    -0.06
    WidthSpace
    -0.06
    ати
    -0.06
     erro
    -0.06
    ressive
    -0.06
    TXT
    -0.06
    embro
    -0.06
    POSITIVE LOGITS
    .Visibility
    0.07
    	resource
    0.07
    ，此
    0.06
     debacle
    0.06
     destruct
    0.06
     galer
    0.06
     rearr
    0.06
    elog
    0.06
     fel
    0.06
    Tcp
    0.06
    Act Density 0.014%

    No Known Activations