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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bam
    -0.07
    -hover
    -0.07
    огод
    -0.07
    líž
    -0.06
     squares
    -0.06
     MOCK
    -0.06
    -China
    -0.06
     φω
    -0.06
    anlık
    -0.06
     Drugs
    -0.06
    POSITIVE LOGITS
     elemento
    0.07
     dokun
    0.06
    plt
    0.06
    >{@
    0.06
     screenSize
    0.06
     opráv
    0.06
     συνο
    0.06
     ofApp
    0.06
    arp
    0.06
    发行
    0.06
    Act Density 0.054%

    No Known Activations