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

    Neuronpedia

    INDEX
    Explanations

    Connecting words or phrases

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ============↵
    -0.07
    Upgrade
    -0.07
     vert
    -0.07
     Serve
    -0.06
     codec
    -0.06
     coral
    -0.06
     Please
    -0.06
     Spare
    -0.06
    Value
    -0.06
    	product
    -0.06
    POSITIVE LOGITS
    ref
    0.06
    .workspace
    0.06
    sand
    0.06
    .AC
    0.06
    ipzig
    0.06
     عش
    0.06
    /mod
    0.06
    ihad
    0.06
    kich
    0.06
    اكم
    0.06
    Act Density 0.041%

    No Known Activations