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

    Neuronpedia

    INDEX
    Explanations

    assets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Literal
    -0.07
     singles
    -0.07
    =${
    -0.07
     Boxes
    -0.06
     inter
    -0.06
     grains
    -0.06
    :host
    -0.06
     TRE
    -0.06
     SELF
    -0.06
    Api
    -0.06
    POSITIVE LOGITS
    .sendStatus
    0.07
     Hilton
    0.06
     mal
    0.06
    luž
    0.06
    	border
    0.06
    .scrollHeight
    0.06
     yytype
    0.06
    尺
    0.06
    　　　　　　　　　　　　　　　　
    0.06
    华
    0.06
    Act Density 0.005%

    No Known Activations